Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    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. 45171
    Prev
    Next
    INDEX
    Explanations

    government and legal terms and actions

    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
    101
    +0.03
    0.6%
    383
    +0.03
    0.5%
    378
    +0.03
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    59
    +0.03
    0.09
    608
    +0.03
    0.17
    566
    +0.03
    0.10
    Negative Logits
    rients
    -0.16
     Presbyter
    -0.16
    coming
    -0.16
    groups
    -0.15
    lif
    -0.15
    benefit
    -0.14
     smokes
    -0.14
    arry
    -0.14
     Krishna
    -0.14
    ————
    -0.14
    POSITIVE LOGITS
    ĸļ
    0.18
     stride
    0.16
    geoning
    0.16
    hearted
    0.15
     fever
    0.15
    ophone
    0.15
     pact
    0.15
     saturation
    0.15
    achi
    0.15
    atsu
    0.15
    Activations Density 9.519%

    No Known Activations