© 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. 33498
    Prev
    Next
    INDEX
    Explanations

    locations or proper nouns

    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
    240
    +0.10
    0.6%
    699
    +0.09
    0.5%
    383
    +0.08
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    288
    +0.10
    0.21
    326
    +0.09
    0.22
    496
    +0.08
    0.16
    Negative Logits
    ably
    -0.67
    AGE
    -0.58
     McMaster
    -0.56
    OPLE
    -0.56
    ensable
    -0.55
    ESE
    -0.55
    IBLE
    -0.53
    aceous
    -0.51
    AGES
    -0.49
    Ø©
    -0.48
    POSITIVE LOGITS
    gard
    0.67
    rang
    0.66
    undai
    0.65
    borg
    0.63
    yk
    0.60
    chel
    0.60
     Ny
    0.59
    gments
    0.57
    seys
    0.56
    ramid
    0.56
    Activations Density 8.047%

    No Known Activations