© 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. 10016
    Prev
    Next
    INDEX
    Explanations

    instances of decisions being made

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "decided" in various contexts

    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
    eries
    -0.64
    anon
    -0.60
    ILA
    -0.59
    iddle
    -0.57
    reen
    -0.56
    oing
    -0.55
    quin
    -0.55
    Lens
    -0.55
    Newsletter
    -0.55
    ighth
    -0.53
    POSITIVE LOGITS
     to
    1.04
     unanimously
    0.86
     against
    0.85
     upon
    0.82
     that
    0.75
     unilaterally
    0.72
     beforehand
    0.69
     not
    0.69
     differently
    0.69
     nevertheless
    0.68
    Activations Density 0.068%

    No Known Activations