© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Apollo Research · Taylor · Identifying Functionally Important Features with End-to-End Sparse Dictionary Learning
    3. GPT2-Small
    4. Residual Similar CE Local
    5. 6-RES_SCL-AJT
    6. 45849
    Prev
    Next
    INDEX
    Explanations

    relationships between different medical conditions, genetic factors, and treatments

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    neuronpedia/gpt2-small__res_scl-ajt/6-res_scl-ajt
    Prompts (Dashboard)
    12,288 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    46,080
    Data Type
    torch.float32
    Hook Point
    blocks.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    apollo-research/Skylion007-openwebtext-tokenizer-gpt2
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    •Layer 6 UMAP region: Local cluster above bottom line touching e2e-recon cluster - local

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    447
    +0.33
    1.8%
    640
    +0.18
    1.0%
    679
    +0.13
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    679
    +0.33
    0.35
    6
    +0.18
    0.32
    640
    +0.13
    0.33
    Negative Logits
     dime
    -0.72
     estate
    -0.72
     hug
    -0.65
    enged
    -0.62
     extortion
    -0.60
     shove
    -0.60
     dirt
    -0.60
     grain
    -0.59
     unstoppable
    -0.59
     rallying
    -0.59
    POSITIVE LOGITS
     Moreover
    1.22
     Therefore
    1.21
     Furthermore
    1.21
     Thus
    1.16
     However
    1.16
     Consequently
    1.16
     Additionally
    1.12
     Nevertheless
    1.11
     Accordingly
    1.10
     Although
    1.08
    Activations Density 8.274%

    No Known Activations