Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 11-RES-JB
    6. 17004
    Prev
    Next
    INDEX
    Explanations

    points in time or instances of events

    oai_token-act-pair · gpt-3.5-turbo

    mentions of specific moments or instances in time

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ords
    -0.67
    yet
    -0.65
    uno
    -0.64
    atts
    -0.63
    GES
    -0.63
    ÃŁ
    -0.60
    Frames
    -0.60
    advertisement
    -0.58
    rats
    -0.58
    galitarian
    -0.58
    POSITIVE LOGITS
     during
    1.16
     throughout
    0.89
     ago
    0.87
     thereafter
    0.82
     apiece
    0.77
     along
    0.76
    during
    0.74
     midway
    0.73
     glance
    0.71
    arf
    0.70
    Activations Density 0.059%

    No Known Activations