© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 4-RES-JB
    11. 7112
    Prev
    Next
    INDEX
    Explanations

    instances where the text prompts the reader to take action

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating readiness or willingness to participate in an activity

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

    No Comments

    Negative Logits
    orp
    -0.73
    roma
    -0.72
    orb
    -0.72
    oret
    -0.69
    agram
    -0.66
    ĸļ
    -0.65
    orean
    -0.65
    attribute
    -0.65
    auri
    -0.64
    ischer
    -0.63
    POSITIVE LOGITS
     Ready
    0.98
    Ready
    0.91
    itude
    0.81
    arity
    0.78
    ready
    0.77
     ready
    0.75
    housing
    0.70
    fort
    0.67
    wired
    0.66
    fire
    0.66
    Activations Density 0.015%

    No Known Activations