© 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. 33132
    Prev
    Next
    INDEX
    Explanations

    words related to physical recovery and health

    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
    +0.18
    1.1%
    382
    +0.08
    0.5%
    481
    +0.08
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    665
    +0.18
    0.14
    526
    +0.08
    -0.06
    59
    +0.08
    0.07
    Negative Logits
    pg
    -0.59
    inho
    -0.55
    alde
    -0.48
    Sport
    -0.47
    roller
    -0.47
    orter
    -0.46
    unless
    -0.46
     bandwagon
    -0.46
    mpire
    -0.46
    adj
    -0.45
    POSITIVE LOGITS
    é¾įå
    0.51
     unsuccessfully
    0.51
    ©¶æ
    0.50
    itially
    0.49
     comprom
    0.49
    ricanes
    0.49
     awhile
    0.48
    ãĤ¢ãĥ«
    0.47
     Pengu
    0.46
     unsuccessful
    0.46
    Activations Density 7.818%

    No Known Activations