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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 36177
    Prev
    Next
    INDEX
    Explanations

    information related to video game enhancements and adjustments, particularly focusing on targets, abilities, and effects

    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
    +0.12
    0.8%
    581
    +0.07
    0.4%
    737
    +0.07
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    741
    +0.12
    0.09
    515
    +0.07
    0.12
    19
    +0.07
    0.08
    Negative Logits
    ories
    -0.53
     symbolism
    -0.47
    utherland
    -0.45
    soDeliveryDate
    -0.45
    使
    -0.45
    creen
    -0.43
    utic
    -0.43
     indo
    -0.43
     symbolic
    -0.43
    èª
    -0.42
    POSITIVE LOGITS
     respawn
    0.56
    bane
    0.52
    Unit
    0.50
     summoned
    0.48
     spawn
    0.48
    aur
    0.47
     Mech
    0.46
    NAME
    0.46
    yle
    0.46
     spawns
    0.45
    Activations Density 9.951%

    No Known Activations