© 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. 7-RES-JB
    11. 23841
    Prev
    Next
    INDEX
    Explanations

    proper nouns and instances of statements referring to an official declaration

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "declare" and its variations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ĸļ
    -0.70
    RH
    -0.68
    alez
    -0.68
    pps
    -0.67
    ramid
    -0.67
    umbn
    -0.67
     Leone
    -0.66
    Pg
    -0.66
    Reply
    -0.66
    dayName
    -0.63
    POSITIVE LOGITS
     bankruptcy
    0.93
     allegiance
    0.90
    phas
    0.84
    ignty
    0.80
     martial
    0.76
     unequivocally
    0.75
     aloud
    0.75
     unconstitutional
    0.74
    arations
    0.74
     war
    0.73
    Activations Density 0.035%

    No Known Activations