© 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. 39998
    Prev
    Next
    INDEX
    Explanations

    PMs (Private Messages) with an attention rate of instances of offensive or personal attacks

    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
    649
    +0.08
    0.5%
    10
    +0.07
    0.5%
    381
    +0.06
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    530
    +0.08
    0.05
    649
    +0.07
    0.03
    326
    +0.06
    0.18
    Negative Logits
     defic
    -0.52
     thous
    -0.45
    itary
    -0.45
     fu
    -0.44
     Salman
    -0.43
     Volks
    -0.43
     Haram
    -0.43
     stead
    -0.42
     tissues
    -0.42
     pestic
    -0.41
    POSITIVE LOGITS
    oshenko
    0.59
    OPS
    0.57
    ulhu
    0.53
    USH
    0.52
    estern
    0.52
    OE
    0.50
    oday
    0.49
    IME
    0.49
    OLOGY
    0.48
    KI
    0.48
    Activations Density 6.227%

    No Known Activations