© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 31515
    Prev
    Next
    INDEX
    Explanations

    terms and names associated with Stanford University

    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
    +0.18
    0.8%
    288
    +0.17
    0.8%
    224
    +0.12
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    288
    +0.18
    0.21
    224
    +0.17
    0.09
    46
    +0.12
    0.07
    Negative Logits
    hops
    -0.86
    alez
    -0.82
    ocre
    -0.75
    usting
    -0.73
    htar
    -0.73
    pelled
    -0.72
    ombo
    -0.69
     administr
    -0.69
    ovych
    -0.68
     livest
    -0.68
    POSITIVE LOGITS
     Cardinal
    0.85
     Institution
    0.85
     Linear
    0.80
     Alto
    0.77
     Prison
    0.76
     University
    0.75
    thal
    0.73
     Encyclopedia
    0.72
    Zen
    0.71
    ford
    0.71
    Activations Density 6.970%

    No Known Activations