© 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. 20272
    Prev
    Next
    INDEX
    Explanations

    references to individuals or groups of people in a legal or investigative context

    oai_token-act-pair · gpt-3.5-turbo

    references to liability and responsibility in communication

    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
     bleak
    -0.73
    interstitial
    -0.71
     Expand
    -0.68
    Growing
    -0.67
    Weak
    -0.66
     Tow
    -0.66
     utopian
    -0.65
     fascinating
    -0.63
     gloomy
    -0.63
     relegation
    -0.63
    POSITIVE LOGITS
     acted
    1.46
     complied
    1.46
     participated
    1.39
     violated
    1.33
     did
    1.32
     knew
    1.32
     interacted
    1.25
     lied
    1.24
     voluntarily
    1.22
     chose
    1.22
    Activations Density 0.571%

    No Known Activations