© 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. 31638
    Prev
    Next
    INDEX
    Explanations

    locations or places

    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
    +0.16
    0.8%
    526
    +0.10
    0.5%
    549
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    326
    +0.16
    0.23
    201
    +0.10
    0.09
    288
    +0.10
    0.21
    Negative Logits
    lessly
    -0.88
    ritional
    -0.68
     satell
    -0.65
    ramer
    -0.64
    ician
    -0.64
    gement
    -0.63
    LESS
    -0.62
    mingham
    -0.62
    amental
    -0.62
    itudinal
    -0.61
    POSITIVE LOGITS
    emon
    0.76
    ombie
    0.76
    ombies
    0.72
     Motorsport
    0.72
    Ga
    0.69
    plain
    0.69
    eta
    0.69
    quez
    0.68
    eb
    0.67
    illes
    0.67
    Activations Density 8.994%

    No Known Activations