© 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 E2E Recon
    9. 6-RES_SCEFR-AJT
    11. 2062
    Prev
    Next
    INDEX
    Explanations

    references to player and character attributes in gaming environments

    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
    216
    +0.18
    0.7%
    575
    +0.14
    0.5%
    189
    +0.14
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    189
    +0.18
    0.06
    575
    +0.14
    0.07
    216
    +0.14
    0.06
    Negative Logits
    ¿½
    -1.00
    ories
    -0.98
     Beir
    -0.94
    į
    -0.90
    ouk
    -0.85
    ½
    -0.84
    azo
    -0.83
    orship
    -0.81
    ¦
    -0.80
    enthal
    -0.77
    POSITIVE LOGITS
    Unknown
    1.08
    player
    1.01
     Piano
    1.00
    unknown
    0.94
    wagen
    0.93
    Alias
    0.91
    players
    0.90
    wright
    0.88
    cript
    0.86
    plays
    0.84
    Activations Density 0.868%

    No Known Activations