© 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. 16491
    Prev
    Next
    INDEX
    Explanations

    uppercase sequences that are likely to be structural formatting or section breaks in text

    oai_token-act-pair · gpt-3.5-turbo

    noun phrases related to criminal activity and ongoing investigations

    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
     subconscious
    -0.80
     systematically
    -0.79
     describ
    -0.78
     spir
    -0.76
     acutely
    -0.76
     structured
    -0.75
     disciplines
    -0.75
     invisible
    -0.75
     analys
    -0.75
     persu
    -0.74
    POSITIVE LOGITS
    Follow
    1.86
    Copyright
    1.79
    Topics
    1.70
    Related
    1.66
    Contact
    1.63
    Thumbnail
    1.62
    Correction
    1.62
    Advertisements
    1.61
    Read
    1.61
    ©
    1.60
    Activations Density 0.338%

    No Known Activations