© 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. 3589
    Prev
    Next
    INDEX
    Explanations

    statements or quotes followed by a full stop

    oai_token-act-pair · gpt-3.5-turbo

    statements that conclude or summarize thoughts

    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
    rive
    -0.78
     torpedo
    -0.78
     runaway
    -0.75
     challeng
    -0.74
    !]
    -0.74
    itely
    -0.73
     brill
    -0.73
    isphere
    -0.73
     matured
    -0.73
    iqu
    -0.72
    POSITIVE LOGITS
     âĢ
    2.21
     ¶
    1.58
    âĢ
    1.45
     **
    1.32
     âĸ
    1.21
     ®
    1.20
     �
    1.19
     âĸº
    1.19
     à¤
    1.18
     âĶ
    1.18
    Activations Density 0.424%

    No Known Activations