© 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. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 11-RES-JB
    11. 20909
    Prev
    Next
    INDEX
    Explanations

    references to locations with a specific abbreviation format

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of statistical references related to locations and reports

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.hook_resid_pre
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    torch.float32
    Hook Point
    blocks.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    mble
    -0.71
    ngth
    -0.70
    eway
    -0.63
     honor
    -0.58
    pter
    -0.57
    dden
    -0.57
    getic
    -0.57
    rolet
    -0.56
    anchez
    -0.55
    =-=-
    -0.55
    POSITIVE LOGITS
    C
    0.85
    Cs
    0.82
    Bs
    0.74
    VI
    0.71
    Tech
    0.69
    Sc
    0.65
    O
    0.64
    S
    0.64
    A
    0.63
    Va
    0.62
    Activations Density 0.034%

    No Known Activations