© 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. 45732
    Prev
    Next
    INDEX
    Explanations

    phrases related to criticism or evaluation of people or situations

    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
    186
    +0.13
    0.6%
    447
    +0.11
    0.5%
    70
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    70
    +0.13
    0.18
    665
    +0.11
    0.17
    140
    +0.11
    0.11
    Negative Logits
    PsyNetMessage
    -0.62
     Stri
    -0.62
    ufact
    -0.61
     Introduced
    -0.60
    riad
    -0.59
    arius
    -0.58
    aret
    -0.58
    ItemTracker
    -0.58
     fielded
    -0.58
     Surv
    -0.57
    POSITIVE LOGITS
    vind
    0.82
     louder
    0.66
    zynski
    0.65
    eworthy
    0.63
    ENC
    0.63
     smarter
    0.62
    ="#
    0.60
    ignore
    0.59
     unwelcome
    0.59
    Agent
    0.58
    Activations Density 12.324%

    No Known Activations