© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 9-RES-JB
    6. 1786
    Prev
    Next
    INDEX
    Explanations

    words related to the process of fermentation

    oai_token-act-pair · gpt-3.5-turbo

    references to processes, events, or entities related to authority, structure, and regulation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ?),
    -0.65
    ?).
    -0.53
    pires
    -0.51
     ?)
    -0.51
    DragonMagazine
    -0.49
    ?)
    -0.49
    hillary
    -0.48
    ©¶æ
    -0.47
     Canaver
    -0.47
    kered
    -0.47
    POSITIVE LOGITS
    .
    1.01
    .[
    0.89
    .(
    0.87
    *.
    0.81
    _.
    0.79
     which
    0.76
     whereas
    0.75
    !.
    0.73
     whilst
    0.72
    ;
    0.72
    Activations Density 1.469%

    No Known Activations