© 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. 35515
    Prev
    Next
    INDEX
    Explanations

    detailed descriptions of specific past events involving individuals and their actions

    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
    +0.32
    1.5%
    393
    +0.17
    0.8%
    362
    +0.14
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    393
    +0.32
    0.38
    397
    +0.17
    0.10
    255
    +0.14
    0.12
    Negative Logits
    iaries
    -0.73
    ulo
    -0.69
    oglu
    -0.67
    ngth
    -0.66
    reviewed
    -0.66
    letcher
    -0.62
     Boyle
    -0.61
    inois
    -0.61
    strom
    -0.60
    FIG
    -0.60
    POSITIVE LOGITS
     impending
    0.88
     upcoming
    0.77
     topic
    0.74
     horizon
    0.72
     daddy
    0.70
     entitle
    0.69
     future
    0.68
     looming
    0.68
     evils
    0.68
     imaginary
    0.67
    Activations Density 22.226%

    No Known Activations