© 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. 39501
    Prev
    Next
    INDEX
    Explanations

    concepts related to objects or locations within a specific context

    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
    311
    +0.15
    0.8%
    59
    +0.11
    0.6%
    26
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    288
    +0.15
    0.20
    326
    +0.11
    0.19
    26
    +0.11
    0.11
    Negative Logits
    aminer
    -0.82
     lag
    -0.67
    DonaldTrump
    -0.62
     Beir
    -0.61
     Rafael
    -0.59
    LOD
    -0.58
    Domin
    -0.58
    arnaev
    -0.58
    oleon
    -0.57
    BIL
    -0.57
    POSITIVE LOGITS
    s
    0.91
    sburg
    0.90
    urn
    0.89
    shire
    0.88
    ysis
    0.86
    ing
    0.84
    eus
    0.82
    mentation
    0.79
    iture
    0.77
    ships
    0.76
    Activations Density 5.984%

    No Known Activations