© 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
    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. 34741
    Prev
    Next
    INDEX
    Explanations

    news articles regarding industrial accidents or environmental issues

    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
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    348
    +0.13
    0.5%
    604
    +0.12
    0.5%
    520
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    148
    +0.13
    0.13
    37
    +0.12
    0.10
    6
    +0.10
    0.12
    Negative Logits
     wedd
    -0.78
    oult
    -0.71
    lean
    -0.70
     Zimmer
    -0.67
     dyed
    -0.67
    gnu
    -0.66
    aucas
    -0.66
    nery
    -0.66
    breeding
    -0.65
    ortunate
    -0.65
    POSITIVE LOGITS
     IMAGES
    1.08
     [+
    0.94
    920
    0.79
    237
    0.78
    877
    0.72
     Introduction
    0.72
    060
    0.72
    776
    0.72
    pmwiki
    0.71
    INGS
    0.71
    Activations Density 6.154%

    No Known Activations