© 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. 32874
    Prev
    Next
    INDEX
    Explanations

    moments of significance or revelation in a narrative 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
    5
    +0.02
    0.5%
    19
    +0.02
    0.5%
    437
    +0.02
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    182
    +0.02
    0.11
    338
    +0.02
    0.11
    168
    +0.02
    0.11
    Negative Logits
    TPPStreamerBot
    -0.21
    ãĥij
    -0.19
    ÙĬ
    -0.18
    REE
    -0.18
    ãĤ´
    -0.18
    PHOTOS
    -0.18
    TAG
    -0.17
    س
    -0.17
    اÙĦ
    -0.17
    ×Ļ
    -0.17
    POSITIVE LOGITS
    auga
    0.17
    */(
    0.17
     you
    0.16
    hand
    0.16
    achy
    0.15
     arrival
    0.15
     ya
    0.15
    illo
    0.15
    rison
    0.15
    omorph
    0.14
    Activations Density 6.110%

    No Known Activations