© 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. 8132
    Prev
    Next
    INDEX
    Explanations

    declarations of intent or strong statements

    oai_token-act-pair · gpt-3.5-turbo

    expressions of disbelief or skepticism

    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
     targeted
    -0.77
     diminishing
    -0.75
    chnology
    -0.73
     waning
    -0.70
     rundown
    -0.69
     benefits
    -0.68
     ranges
    -0.68
     salv
    -0.68
     parallels
    -0.68
     satell
    -0.67
    POSITIVE LOGITS
    cause
    1.19
    ï¸ı
    1.15
    laughs
    1.05
    laugh
    0.98
    Cause
    0.96
    £
    0.91
    why
    0.91
    âľ
    0.89
    ¯
    0.89
    unless
    0.89
    Activations Density 0.174%

    No Known Activations