© 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. 3-RES-JB
    11. 10787
    Prev
    Next
    INDEX
    Explanations

    names of specific products or objects

    oai_token-act-pair · gpt-3.5-turbo

    mentions of specific titles or names, particularly cultural references

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     tremend
    -0.89
    ULE
    -0.82
    çīĪ
    -0.76
    ãĤ£
    -0.76
    Reviewer
    -0.74
    ãĥij
    -0.73
    çķ
    -0.71
    DragonMagazine
    -0.70
    ccording
    -0.70
    ön
    -0.70
    POSITIVE LOGITS
     timelines
    0.75
    avia
    0.70
     Kaine
    0.69
     recipients
    0.67
     Treasurer
    0.65
     Cato
    0.65
    achy
    0.63
     Chair
    0.62
     Trudeau
    0.62
    iam
    0.62
    Activations Density 0.000%

    No Known Activations