© 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
    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. 18758
    Prev
    Next
    INDEX
    Explanations

    references to governmental bodies and official statements

    oai_token-act-pair · gpt-3.5-turbo

    references to formal organizations and institutions related to governance

    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
    $.
    -0.84
    }.
    -0.78
    *.
    -0.70
    >.
    -0.66
    '.
    -0.65
    ĸļ
    -0.65
     ".
    -0.64
    !.
    -0.64
     '.
    -0.64
    ".
    -0.64
    POSITIVE LOGITS
     spokesman
    0.73
     spokeswoman
    0.66
     spokesperson
    0.65
     attorney
    0.60
     acknowledges
    0.54
     tweeted
    0.52
     meanwhile
    0.52
     Oversight
    0.50
     Herald
    0.50
     Accountability
    0.49
    Activations Density 1.337%

    No Known Activations