© 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. 1-RES-JB
    11. 16460
    Prev
    Next
    INDEX
    Explanations

    values corresponding to time (such as hours or dates)

    oai_token-act-pair · gpt-3.5-turbo

    numerical figures or statistics, particularly those formatted as dollar amounts and percentages

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ¥ŀ
    -0.92
     tremend
    -0.90
    ĸļ
    -0.84
    achus
    -0.76
     reluct
    -0.75
    querque
    -0.74
     pse
    -0.73
     volunte
    -0.72
    elong
    -0.72
     nomine
    -0.71
    POSITIVE LOGITS
    00
    1.23
    67
    1.23
    88
    1.22
    89
    1.20
    69
    1.18
    42
    1.18
    83
    1.18
    87
    1.17
    68
    1.17
    41
    1.17
    Activations Density 0.126%

    No Known Activations