© 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. 3799
    Prev
    Next
    INDEX
    Explanations

    links to online sources or articles

    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
    481
    +0.19
    0.8%
    640
    +0.19
    0.8%
    393
    +0.14
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    640
    +0.19
    0.28
    160
    +0.19
    0.21
    393
    +0.14
    0.22
    Negative Logits
     Tenn
    -0.76
     Mara
    -0.75
     Ascension
    -0.74
     Ross
    -0.74
     Weld
    -0.73
     âī¡
    -0.73
     Goo
    -0.69
     Adinida
    -0.69
     Tanz
    -0.69
     Xiao
    -0.69
    POSITIVE LOGITS
    photos
    1.27
    hillary
    1.13
    committee
    1.11
    recomm
    1.10
    gallery
    1.06
    dead
    1.06
    cia
    1.05
    report
    1.03
    voy
    1.03
    terms
    1.02
    Activations Density 10.299%

    No Known Activations