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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 40322
    Prev
    Next
    INDEX
    Explanations

    terms related to dungeons and gameplay elements in a video game 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
    447
    +0.17
    1.0%
    326
    +0.14
    0.8%
    288
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    326
    +0.17
    0.18
    288
    +0.14
    0.17
    211
    +0.12
    -0.01
    Negative Logits
     FTA
    -0.56
    henko
    -0.55
    LM
    -0.55
    onica
    -0.54
    ciation
    -0.53
    chell
    -0.51
     Aad
    -0.50
    lers
    -0.50
    gow
    -0.49
    racted
    -0.49
    POSITIVE LOGITS
     crawl
    0.82
     craw
    0.78
     crawling
    0.76
    geons
    0.72
    geon
    0.69
    Leaks
    0.64
     dungeons
    0.62
     dungeon
    0.60
     Craw
    0.56
     raiding
    0.54
    Activations Density 5.599%

    No Known Activations