© 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. 15720
    Prev
    Next
    INDEX
    Explanations

    descriptions related to political figures or campaigns

    oai_token-act-pair · gpt-3.5-turbo

    sentiments and concepts related to love and unity

    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
    âĢ
    -0.76
    ÂŃ
    -0.72
    ̶
    -0.69
     âĢ
    -0.64
    —
    -0.63
     ðŁ
    -0.62
     âĢķ
    -0.62
    ãĥ
    -0.62
    Ö¼
    -0.61
     ÂŃ
    -0.61
    POSITIVE LOGITS
     Others
    0.77
     others
    0.71
    other
    0.71
    Others
    0.68
     OTHER
    0.66
     pts
    0.65
     Other
    0.60
     oppos
    0.60
     conflicting
    0.58
     Same
    0.56
    Activations Density 1.364%

    No Known Activations