© 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. 24474
    Prev
    Next
    INDEX
    Explanations

    written statements of spoken words

    oai_token-act-pair · gpt-3.5-turbo

    statements or quotations attributed to individuals

    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
     seiz
    -0.94
     Siren
    -0.88
     Venus
    -0.83
     bas
    -0.80
    akra
    -0.78
    onia
    -0.78
     orb
    -0.77
     Zeal
    -0.76
    ophon
    -0.75
     helium
    -0.73
    POSITIVE LOGITS
    Mc
    2.83
     Mc
    2.44
     McC
    2.09
    McC
    2.01
     McN
    1.96
     McD
    1.88
     McK
    1.85
    mc
    1.84
     McL
    1.83
     McG
    1.80
    Activations Density 0.296%

    No Known Activations