© 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. 40486
    Prev
    Next
    INDEX
    Explanations

    phrases describing a high level of intensity or significance

    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
    745
    +0.07
    0.6%
    756
    +0.07
    0.6%
    373
    +0.07
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    373
    +0.07
    -0.14
    252
    +0.07
    0.09
    226
    +0.07
    0.08
    Negative Logits
     dime
    -0.36
    ibrary
    -0.35
     PAY
    -0.33
     Afgh
    -0.32
    Ò
    -0.32
     realities
    -0.31
    å¼
    -0.30
     mole
    -0.30
    umbn
    -0.30
     Bulgarian
    -0.30
    POSITIVE LOGITS
    ndra
    0.38
    arn
    0.37
    ukong
    0.37
    ulture
    0.36
    aan
    0.36
    ahn
    0.36
    ĸļ
    0.36
    ugu
    0.35
    ult
    0.35
     congr
    0.35
    Activations Density 5.756%

    No Known Activations