© 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 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. 33742
    Prev
    Next
    INDEX
    Explanations

    proper nouns related to organizations, individuals, and locations

    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
    +0.24
    1.1%
    99
    +0.15
    0.7%
    326
    +0.14
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    99
    +0.24
    0.09
    326
    +0.15
    0.19
    146
    +0.14
    0.07
    Negative Logits
    ablishment
    -0.83
    stract
    -0.82
    yrinth
    -0.77
    ormon
    -0.74
    aneous
    -0.74
    ebook
    -0.73
    ainer
    -0.73
    aneously
    -0.70
    ormons
    -0.69
    osal
    -0.69
    POSITIVE LOGITS
    burg
    1.16
    port
    0.90
    borg
    0.89
    ports
    0.85
    sey
    0.81
    burgh
    0.80
    manship
    0.79
    combe
    0.74
    bach
    0.73
    kins
    0.72
    Activations Density 7.453%

    No Known Activations