Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 4-RES-JB
    6. 22725
    Prev
    Next
    INDEX
    Explanations

    adjectives related to intense or extreme sensations or actions

    oai_token-act-pair · gpt-3.5-turbo

    intensely descriptive or vivid verbs, particularly those implying heat or movement

    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
    ascript
    -0.92
    ilet
    -0.72
    ilogy
    -0.71
    LR
    -0.71
    uther
    -0.70
    ynthesis
    -0.70
    many
    -0.69
    cci
    -0.68
    ulet
    -0.68
    icians
    -0.67
    POSITIVE LOGITS
     seas
    0.91
    ly
    0.85
     tides
    0.80
    LY
    0.78
     hot
    0.77
     brilliance
    0.74
     torrent
    0.73
     rain
    0.73
     waters
    0.73
    NESS
    0.71
    Activations Density 0.102%

    No Known Activations