© 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. 9883
    Prev
    Next
    INDEX
    Explanations

    references to specific information or facts being highlighted or emphasized

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "point" and its variations

    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
    natureconservancy
    -0.81
     seiz
    -0.77
    ccording
    -0.72
     ILCS
    -0.65
    OOL
    -0.62
    lap
    -0.61
    earable
    -0.60
    ourt
    -0.60
    ottest
    -0.60
    lishes
    -0.59
    POSITIVE LOGITS
     fingers
    1.19
     out
    1.10
     toward
    0.98
     towards
    0.98
     finger
    0.91
     to
    0.83
    lessly
    0.79
     blank
    0.74
    edly
    0.73
    ly
    0.73
    Activations Density 0.044%

    No Known Activations