© 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. 32875
    Prev
    Next
    INDEX
    Explanations

    specific instances of being tied or attached to something

    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
    +0.14
    0.8%
    581
    +0.10
    0.5%
    362
    +0.08
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    393
    +0.14
    0.33
    362
    +0.10
    0.17
    608
    +0.08
    0.21
    Negative Logits
    inventoryQuantity
    -0.63
    TPPStreamerBot
    -0.62
    amaz
    -0.61
     VIDEOS
    -0.61
    xp
    -0.61
    assing
    -0.61
    emouth
    -0.60
    Draft
    -0.60
    ceivable
    -0.60
    parency
    -0.59
    POSITIVE LOGITS
     knots
    0.76
     knot
    0.69
     underside
    0.68
     pins
    0.61
     peg
    0.61
     leash
    0.60
     removable
    0.58
     tightly
    0.58
    elin
    0.57
     wagon
    0.56
    Activations Density 16.480%

    No Known Activations