© 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. 8-RES-JB
    11. 9910
    Prev
    Next
    INDEX
    Explanations

    statements expressing agreement

    oai_token-act-pair · gpt-3.5-turbo

    expressions of agreement

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     typh
    -0.79
    gins
    -0.71
    oufl
    -0.71
     Gutenberg
    -0.65
     Roads
    -0.65
    agin
    -0.65
    anus
    -0.65
    ogo
    -0.63
    thur
    -0.61
    æµ
    -0.61
    POSITIVE LOGITS
     vehemently
    0.89
    ably
    0.81
     disagree
    0.80
    lihood
    0.79
     unanimously
    0.76
    rences
    0.76
    SOURCE
    0.75
    abl
    0.69
    atively
    0.68
    ault
    0.68
    Activations Density 0.046%

    No Known Activations