© 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. 13073
    Prev
    Next
    INDEX
    Explanations

    business partnerships and collaborations

    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
    +0.28
    1.3%
    247
    +0.11
    0.5%
    656
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    656
    +0.28
    0.07
    247
    +0.11
    0.05
    465
    +0.10
    0.04
    Negative Logits
    aston
    -0.77
    ux
    -0.75
    cale
    -0.74
    SpaceEngineers
    -0.71
    ihil
    -0.71
    pmwiki
    -0.70
     oxide
    -0.69
    ombie
    -0.69
    kefeller
    -0.68
    iter
    -0.67
    POSITIVE LOGITS
     partner
    1.06
     partners
    1.00
     Partner
    0.78
    hips
    0.74
    loo
    0.67
    itute
    0.67
    ially
    0.66
     Kel
    0.65
    atively
    0.65
    heses
    0.65
    Activations Density 4.882%

    No Known Activations