© 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. 13629
    Prev
    Next
    INDEX
    Explanations

    names or words ending in "z" followed by a high activation value

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the letter 'z' in various contexts

    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
     Scots
    -0.63
     Southeast
    -0.61
     ransom
    -0.61
     entail
    -0.60
     butt
    -0.59
     foss
    -0.55
     behavi
    -0.53
     foremost
    -0.53
     qualitative
    -0.53
     sane
    -0.52
    POSITIVE LOGITS
    enegger
    1.39
    ombie
    1.33
    gerald
    1.20
    ewski
    1.18
    ombies
    1.17
    ymes
    1.14
    alez
    1.10
    ebra
    1.03
    ealous
    1.03
    hao
    1.03
    Activations Density 0.068%

    No Known Activations