© 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. 13422
    Prev
    Next
    INDEX
    Explanations

    numbered lists

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of numeric values or coded references

    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
    hement
    -0.83
     undermin
    -0.71
    obbies
    -0.69
     diving
    -0.65
    abwe
    -0.62
     dissu
    -0.62
    hetti
    -0.61
     steroids
    -0.61
    userc
    -0.60
     wanting
    -0.60
    POSITIVE LOGITS
    ³³³³³³³³
    1.10
    ³³³³
    1.08
    ³³³
    1.08
    ³³³³³³³³³³³³³³³³
    1.05
     largeDownload
    0.84
    ccording
    0.83
    pmwiki
    0.82
    ³³
    0.79
    Anonymous
    0.78
    Palestinian
    0.73
    Activations Density 0.122%

    No Known Activations