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

    Neuronpedia

    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. 39430
    Prev
    Next
    INDEX
    Explanations

    references to specific locations or organizations

    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
    +0.29
    1.4%
    631
    +0.11
    0.5%
    747
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    183
    +0.29
    0.12
    755
    +0.11
    0.08
    631
    +0.10
    0.10
    Negative Logits
    etheless
    -0.77
    OPLE
    -0.70
     afar
    -0.64
     lett
    -0.61
     writ
    -0.59
     noses
    -0.58
    tenance
    -0.58
     ..............
    -0.58
     needles
    -0.57
    ç·
    -0.56
    POSITIVE LOGITS
    alf
    0.86
    edes
    0.84
    omer
    0.84
    ob
    0.83
    oran
    0.83
    uber
    0.82
    omal
    0.82
    ussie
    0.82
    rit
    0.82
    ros
    0.81
    Activations Density 13.282%

    No Known Activations