© 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. 4100
    Prev
    Next
    INDEX
    Explanations

    mentions of press conferences or statements made to journalists

    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
    447
    +0.27
    1.6%
    483
    +0.08
    0.5%
    298
    +0.08
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    554
    +0.27
    -0.10
    765
    +0.08
    0.10
    274
    +0.08
    0.09
    Negative Logits
    tein
    -0.54
    oute
    -0.53
    ez
    -0.50
     Lives
    -0.49
    inho
    -0.46
     Feminist
    -0.46
    course
    -0.45
     Femin
    -0.45
     lives
    -0.44
     Bastard
    -0.44
    POSITIVE LOGITS
    perty
    0.65
     onstage
    0.55
    ubs
    0.55
    orage
    0.53
     afterward
    0.53
    aptic
    0.53
     conference
    0.52
     aboard
    0.50
     plaza
    0.50
    odder
    0.50
    Activations Density 9.860%

    No Known Activations