© 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. 14275
    Prev
    Next
    INDEX
    Explanations

    mentions of the video game "Mirror's Edge"

    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
    238
    +0.19
    0.7%
    571
    +0.18
    0.7%
    288
    +0.16
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    288
    +0.19
    0.08
    538
    +0.18
    0.05
    326
    +0.16
    0.06
    Negative Logits
    ential
    -1.02
    xit
    -0.98
    ynes
    -0.94
    adding
    -0.92
    mson
    -0.89
    ndra
    -0.87
    cific
    -0.86
    erent
    -0.84
    mercial
    -0.84
    yright
    -0.83
    POSITIVE LOGITS
    ror
    1.24
    acles
    1.20
    acle
    1.14
    rored
    1.04
    rors
    1.04
    angelo
    1.03
     Abram
    0.92
     shine
    0.91
    ion
    0.90
     maiden
    0.90
    Activations Density 0.867%

    No Known Activations