© 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. 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. 23026
    Prev
    Next
    INDEX
    Explanations

    proper nouns or names

    oai_token-act-pair · gpt-3.5-turbo

    repeated sequences of letters 'll' and 'ell' 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
     quo
    -0.71
    [_
    -0.69
    rely
    -0.62
    benefit
    -0.61
     Kou
    -0.59
     conformity
    -0.57
    displayText
    -0.57
    )].
    -0.56
    Chan
    -0.56
    hered
    -0.55
    POSITIVE LOGITS
    owship
    1.31
    oyd
    1.16
    uminati
    1.16
    ibrary
    1.12
    ounge
    1.10
    ibr
    1.07
    ength
    1.06
    ows
    1.06
    ipop
    1.01
    iard
    0.99
    Activations Density 0.057%

    No Known Activations