© 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. 3788
    Prev
    Next
    INDEX
    Explanations

    words related to wires or wire-like structures

    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
    361
    +0.02
    0.4%
    516
    +0.02
    0.4%
    225
    +0.02
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    640
    +0.02
    0.34
    578
    +0.02
    0.06
    64
    +0.02
    -0.27
    Negative Logits
    liga
    -0.14
     Remastered
    -0.13
    nces
    -0.13
    ffect
    -0.13
     seas
    -0.13
    eatures
    -0.12
    terday
    -0.12
    stall
    -0.12
    AppData
    -0.12
    BLIC
    -0.12
    POSITIVE LOGITS
    ues
    0.17
    ancial
    0.14
    alsa
    0.14
    ument
    0.14
     grill
    0.13
    acle
    0.13
     whine
    0.13
    uctor
    0.13
     band
    0.13
     sled
    0.13
    Activations Density 14.466%

    No Known Activations