© 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. 34462
    Prev
    Next
    INDEX
    Explanations

    phrases indicating worthiness or deservingness

    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
    +0.11
    0.7%
    669
    +0.09
    0.5%
    719
    +0.08
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    393
    +0.11
    0.28
    669
    +0.09
    0.09
    697
    +0.08
    0.06
    Negative Logits
    ullivan
    -0.57
    glers
    -0.53
     synchronized
    -0.51
    nels
    -0.50
     interstate
    -0.48
     portals
    -0.47
    lems
    -0.47
     processes
    -0.46
    uthor
    -0.46
     surfing
    -0.46
    POSITIVE LOGITS
     praise
    0.65
     scorn
    0.61
     ridicule
    0.58
    $$$$
    0.55
    COMPLE
    0.55
     criticism
    0.54
    cipled
    0.54
    cellence
    0.54
    inement
    0.53
    ortality
    0.53
    Activations Density 11.477%

    No Known Activations