© 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. 4-RES-JB
    11. 10263
    Prev
    Next
    INDEX
    Explanations

    comments section prompts and interactions

    oai_token-act-pair · gpt-3.5-turbo

    mentions of comments or requests for interaction in the comments section

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

    No Comments

    Negative Logits
     Recon
    -0.73
    ccording
    -0.73
     Sinai
    -0.67
    ça
    -0.65
    owship
    -0.65
     Reborn
    -0.64
     abduction
    -0.64
    icz
    -0.64
     Ballistic
    -0.64
    isen
    -0.64
    POSITIVE LOGITS
     comments
    0.95
    comments
    0.89
     comment
    0.87
     commenters
    0.85
    ariat
    0.82
    Comment
    0.81
     sections
    0.80
     Comments
    0.79
     commenter
    0.78
     Username
    0.77
    Activations Density 0.032%

    No Known Activations