© 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
    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. 14176
    Prev
    Next
    INDEX
    Explanations

    technical instructions related to computing processes

    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
    651
    +0.05
    0.5%
    503
    +0.05
    0.5%
    232
    +0.04
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    640
    +0.05
    0.22
    186
    +0.05
    0.09
    145
    +0.04
    0.08
    Negative Logits
     overhead
    -0.36
    Reviewer
    -0.30
     mercury
    -0.29
    pheus
    -0.29
    avorite
    -0.29
     employment
    -0.28
     box
    -0.28
     owl
    -0.28
     antitrust
    -0.27
     perfection
    -0.27
    POSITIVE LOGITS
    aring
    0.46
    ined
    0.44
    inelli
    0.43
    ared
    0.41
    ulsion
    0.40
    uilding
    0.39
    zie
    0.39
    oked
    0.38
    are
    0.37
    ination
    0.37
    Activations Density 8.330%

    No Known Activations