© 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. 11541
    Prev
    Next
    INDEX
    Explanations

    hints or references

    oai_token-act-pair · gpt-3.5-turbo

    references to clues or indicators about future events

    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
    fare
    -0.71
    lux
    -0.70
    CENT
    -0.70
    rior
    -0.68
    vict
    -0.67
    nea
    -0.66
    ccording
    -0.63
    portion
    -0.62
    artney
    -0.62
    quished
    -0.61
    POSITIVE LOGITS
     hint
    1.42
     hints
    1.22
     clue
    0.98
    llor
    0.85
     clues
    0.84
    ibility
    0.84
     hinted
    0.81
    ariat
    0.80
    ibly
    0.79
     glimps
    0.74
    Activations Density 0.042%

    No Known Activations