© 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. 4-RES-JB
    11. 15256
    Prev
    Next
    INDEX
    Explanations

    expressions of satisfaction or contentment

    oai_token-act-pair · gpt-3.5-turbo

    expressions of gratitude or relief

    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
     helicop
    -0.83
    improve
    -0.72
    heat
    -0.68
    Improve
    -0.65
    effic
    -0.64
    $$$$
    -0.62
    cend
    -0.61
    eas
    -0.61
     haz
    -0.60
    artifacts
    -0.60
    POSITIVE LOGITS
     glad
    0.91
    withstanding
    0.72
    imar
    0.72
    imaru
    0.72
    ness
    0.72
    dy
    0.71
    ा
    0.69
    terday
    0.69
    bringer
    0.69
    joy
    0.69
    Activations Density 0.016%

    No Known Activations