© 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. 21191
    Prev
    Next
    INDEX
    Explanations

    words related to music, characters, and events likely from a creative or entertainment context

    oai_token-act-pair · gpt-3.5-turbo

    recurring syllable patterns in words

    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
    manship
    -0.74
    owship
    -0.68
    space
    -0.68
    t
    -0.67
    drawn
    -0.67
    mable
    -0.65
    band
    -0.64
    nesday
    -0.63
    taker
    -0.63
    pick
    -0.63
    POSITIVE LOGITS
    zzi
    1.49
    ÄŁ
    1.37
    vernment
    1.13
    zzo
    1.10
    zzle
    1.08
    ires
    1.04
    za
    1.04
    orthy
    1.03
    jo
    1.03
    ffic
    1.02
    Activations Density 0.174%

    No Known Activations