© 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. 21427
    Prev
    Next
    INDEX
    Explanations

    references to research studies or reports

    oai_token-act-pair · gpt-3.5-turbo

    references to reports and studies

    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
    afety
    -0.79
    ecause
    -0.66
    cale
    -0.65
    iege
    -0.65
    conservancy
    -0.63
    ordinate
    -0.62
    ystem
    -0.60
    omething
    -0.59
    uddenly
    -0.58
    always
    -0.58
    POSITIVE LOGITS
     released
    0.90
     published
    0.87
     cited
    0.82
    released
    0.82
     reproduced
    0.82
     obtained
    0.81
     authored
    0.81
     reprinted
    0.80
     reviewed
    0.77
     itself
    0.77
    Activations Density 0.153%

    No Known Activations