© 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. 9-RES-JB
    11. 21175
    Prev
    Next
    INDEX
    Explanations

    references to political leaders or entities

    oai_token-act-pair · gpt-3.5-turbo

    instances of political disappointment or criticism

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Different
    -0.65
    Specific
    -0.65
    rowth
    -0.65
     customized
    -0.64
    ãĤ¼ãĤ¦ãĤ¹
    -0.63
     specialized
    -0.62
    Types
    -0.61
     ranges
    -0.61
     facilit
    -0.60
    similar
    -0.60
    POSITIVE LOGITS
     apology
    0.85
     apologies
    0.82
     resignation
    0.79
     Corbyn
    0.73
     Gawker
    0.72
     disappointing
    0.71
     apologise
    0.71
     Whedon
    0.71
     apologised
    0.70
     decency
    0.70
    Activations Density 1.213%

    No Known Activations