Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    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. 4187
    Prev
    Next
    INDEX
    Explanations

    items and attributes in an online game inventory

    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
    640
    +0.23
    1.0%
    160
    +0.14
    0.6%
    238
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    640
    +0.23
    0.28
    160
    +0.14
    0.20
    373
    +0.10
    -0.12
    Negative Logits
    ĸļ
    -1.03
    ileaks
    -0.89
    lihood
    -0.89
     nomine
    -0.86
     horizont
    -0.77
     pse
    -0.76
     volunt
    -0.75
    cules
    -0.73
     verbs
    -0.72
     secondly
    -0.72
    POSITIVE LOGITS
    Players
    0.98
    unch
    0.94
    Improved
    0.93
    Increases
    0.90
    Default
    0.88
    Aim
    0.86
    Game
    0.85
    Gameplay
    0.79
    Scope
    0.79
    Weapon
    0.78
    Activations Density 5.357%

    No Known Activations