© 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
    2. Apollo Research · Taylor · Identifying Functionally Important Features with End-to-End Sparse Dictionary Learning
    3. GPT2-Small
    4. Residual Similar CE Local
    5. 6-RES_SCL-AJT
    6. 12840
    Prev
    Next
    INDEX
    Explanations

    phrases related to stories, events, and actions happening

    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
    650
    +0.12
    0.8%
    447
    +0.12
    0.7%
    314
    +0.09
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    675
    +0.12
    0.22
    650
    +0.12
    0.20
    53
    +0.09
    0.17
    Negative Logits
     trainers
    -0.50
     unborn
    -0.50
     trolls
    -0.49
     scissors
    -0.48
     limb
    -0.47
     scoreboard
    -0.47
     lingu
    -0.47
     reflex
    -0.47
     purpose
    -0.47
     orcs
    -0.47
    POSITIVE LOGITS
    ï¸ı
    0.68
    uthor
    0.68
    Gi
    0.62
    lux
    0.61
    ternity
    0.61
    cffffcc
    0.60
    Export
    0.56
    estern
    0.56
    Sa
    0.56
    oward
    0.55
    Activations Density 4.692%

    No Known Activations