© 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. 1-RES-JB
    11. 24227
    Prev
    Next
    INDEX
    Explanations

    phrases related to readiness to act or accommodate

    oai_token-act-pair · gpt-3.5-turbo

    expressions of willingness or readiness to act

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    icle
    -0.86
    icles
    -0.72
    inas
    -0.72
    gran
    -0.70
     Sections
    -0.69
     Regions
    -0.68
     Neb
    -0.68
    adish
    -0.67
    idden
    -0.67
     Anthem
    -0.64
    POSITIVE LOGITS
     willingness
    1.12
     unwillingness
    0.94
     guiActiveUn
    0.92
    yip
    0.90
    ï¸
    0.89
     attitude
    0.88
     incent
    0.83
     unden
    0.82
     reluct
    0.80
     reluctance
    0.79
    Activations Density 0.004%

    No Known Activations