© 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. 33993
    Prev
    Next
    INDEX
    Explanations

    technical terms related to research methodology and medical studies

    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
    +0.15
    0.8%
    575
    +0.10
    0.5%
    59
    +0.09
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    640
    +0.15
    0.26
    255
    +0.10
    0.11
    160
    +0.09
    0.20
    Negative Logits
    atron
    -0.58
    zos
    -0.58
    Closure
    -0.57
    azon
    -0.57
    inx
    -0.56
    ulic
    -0.56
    adena
    -0.54
    ysics
    -0.54
    alore
    -0.54
    ophobia
    -0.54
    POSITIVE LOGITS
     mice
    0.61
    otype
    0.60
     laboratory
    0.58
     baseline
    0.58
    imental
    0.57
     serum
    0.56
    bred
    0.55
     Reds
    0.54
     subjects
    0.53
     males
    0.52
    Activations Density 11.847%

    No Known Activations