© 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 E2E Recon
    9. 6-RES_SCEFR-AJT
    11. 5834
    Prev
    Next
    INDEX
    Explanations

    specific video game titles and related terms, with a focus on action and adventure games

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    neuronpedia/gpt2-small__res_scefr-ajt/6-res_scefr-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
    514
    +0.14
    0.5%
    447
    +0.14
    0.5%
    379
    +0.13
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    326
    +0.14
    0.06
    288
    +0.14
    0.07
    556
    +0.13
    0.05
    Negative Logits
    agogue
    -1.05
    umbn
    -1.01
    ajor
    -0.97
    ibrary
    -0.97
    uckland
    -0.93
    ettlement
    -0.93
    aways
    -0.93
    govtrack
    -0.92
    erk
    -0.91
    aspberry
    -0.91
    POSITIVE LOGITS
    Mania
    1.17
     Tactics
    1.17
     Universe
    1.15
     Generations
    1.13
    mania
    1.12
     Characters
    1.11
    ®
    1.11
     ®
    1.09
     Kinect
    1.07
     XIV
    1.07
    Activations Density 0.771%

    No Known Activations