© 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. 1007
    Prev
    Next
    INDEX
    Explanations

    actions of reversal or change

    oai_token-act-pair · gpt-3.5-turbo

    terms related to changing or reversing decisions or courses of action

    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
    shaw
    -0.73
    »Ĵ
    -0.68
    forums
    -0.67
     arenas
    -0.67
     kitchens
    -0.64
    7601
    -0.64
     Cage
    -0.63
    other
    -0.61
    azines
    -0.60
    weather
    -0.60
    POSITIVE LOGITS
     fortunes
    0.93
     course
    0.83
     longstanding
    0.81
     favor
    0.76
     centuries
    0.74
     defaults
    0.72
     decree
    0.72
     millennia
    0.70
    statement
    0.69
     favour
    0.69
    Activations Density 0.177%

    No Known Activations