© 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. 6337
    Prev
    Next
    INDEX
    Explanations

    names of songs or movies

    oai_token-act-pair · gpt-3.5-turbo

    references to specific artists or groups within music

    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
     forwarded
    -0.76
     systematic
    -0.73
     ISPs
    -0.71
     forwards
    -0.71
     forward
    -0.71
     initially
    -0.69
     approx
    -0.69
     parity
    -0.69
     referrals
    -0.68
     expressed
    -0.68
    POSITIVE LOGITS
    ombie
    1.29
    razy
    1.26
    umble
    1.26
    ookie
    1.23
    appy
    1.23
    inky
    1.23
    ambo
    1.23
    umbo
    1.21
    oodoo
    1.20
    unk
    1.20
    Activations Density 0.190%

    No Known Activations