© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Apollo Research · Taylor · Identifying Functionally Important Features with End-to-End Sparse Dictionary Learning
    3. GPT2-Small
    4. Residual Similar CE Local
    5. 6-RES_SCL-AJT
    6. 32884
    Prev
    Next
    INDEX
    Explanations

    questions prompting a response

    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
    391
    +0.14
    0.6%
    703
    +0.13
    0.5%
    332
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    393
    +0.14
    0.20
    391
    +0.13
    0.04
    739
    +0.10
    0.03
    Negative Logits
    ources
    -0.78
    Flags
    -0.77
    NAS
    -0.76
    sych
    -0.76
    JUST
    -0.74
    Cross
    -0.72
    rees
    -0.71
    imil
    -0.71
    Unix
    -0.71
    Beck
    -0.71
    POSITIVE LOGITS
     Bleach
    0.82
     princip
    0.79
    !:
    0.78
     Explain
    0.77
     Feedback
    0.76
    eeee
    0.74
     hither
    0.74
    ivia
    0.73
     Mechdragon
    0.73
     Bulgaria
    0.73
    Activations Density 7.227%

    No Known Activations