© 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. 11-RES-JB
    11. 4103
    Prev
    Next
    INDEX
    Explanations

    mentions of locations or places and professions or roles

    oai_token-act-pair · gpt-3.5-turbo

    references to individuals and their actions or relationships

    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
     âī
    -0.62
     meanwhile
    -0.61
     ÂŃ
    -0.61
     Commissioner
    -0.57
     101
    -0.56
     midst
    -0.55
     antioxid
    -0.55
     123
    -0.54
     clin
    -0.54
     pursuant
    -0.53
    POSITIVE LOGITS
    ts
    1.29
    gs
    1.27
    ios
    1.20
    ø
    1.18
    Ă
    1.17
    Đ
    1.17
    ă
    1.17
    Č
    1.17
    ù
    1.17
    Ě
    1.17
    Activations Density 0.950%

    No Known Activations