© 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. 10-RES-JB
    11. 16350
    Prev
    Next
    INDEX
    Explanations

    dates and technical details

    oai_token-act-pair · gpt-3.5-turbo

    references to specific time periods or dates

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ERC
    -0.70
     Lauder
    -0.65
    wear
    -0.61
     Spielberg
    -0.60
     DeVos
    -0.60
     leveraging
    -0.60
     memor
    -0.59
     Pulitzer
    -0.59
     DOE
    -0.58
     Nieto
    -0.58
    POSITIVE LOGITS
     moderator
    0.93
    ombat
    0.92
     replies
    0.89
    Reply
    0.85
     reply
    0.85
    reply
    0.83
     Posts
    0.83
     Reply
    0.82
    Comment
    0.82
    Joined
    0.78
    Activations Density 0.150%

    No Known Activations