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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Apollo Research · Taylor · Identifying Functionally Important Features with End-to-End Sparse Dictionary Learning
    5. GPT2-Small
    7. Residual Similar CE Local
    9. 6-RES_SCL-AJT
    11. 39645
    Prev
    Next
    INDEX
    Explanations

    conversations and dialogues between characters

    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: Mostly-local line at bottom - local

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    447
    +0.29
    3.3%
    87
    +0.27
    3.0%
    64
    +0.21
    2.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    87
    +0.29
    -0.04
    464
    +0.27
    0.19
    218
    +0.21
    0.10
    Negative Logits
    quartered
    -0.26
    utterstock
    -0.26
     Communities
    -0.25
     policymakers
    -0.25
    bitious
    -0.24
     reliance
    -0.24
     Infrastructure
    -0.23
    anwhile
    -0.23
     Dhabi
    -0.23
     reliant
    -0.23
    POSITIVE LOGITS
    ITNESS
    0.33
     fuckin
    0.27
     ;)
    0.27
     bitch
    0.27
     tho
    0.25
     whore
    0.25
     negro
    0.24
     whats
    0.24
     sten
    0.24
     :(
    0.24
    Activations Density 12.462%

    No Known Activations