© 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. 13071
    Prev
    Next
    INDEX
    Explanations

    words or terms related to gardening

    oai_token-act-pair · gpt-3.5-turbo

    references to Gnosticism and related concepts

    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
    WHERE
    -0.83
    manship
    -0.71
     Rash
    -0.69
    Materials
    -0.67
     Gamble
    -0.67
    LIST
    -0.65
    BRE
    -0.63
    FLAG
    -0.63
    FINE
    -0.62
    âĢ¢âĢ¢âĢ¢âĢ¢
    -0.62
    POSITIVE LOGITS
    ostic
    1.21
    osis
    1.05
    ostics
    0.98
    omon
    0.96
    ome
    0.95
    gling
    0.94
    ogly
    0.93
    acles
    0.91
    emonic
    0.90
    agons
    0.88
    Activations Density 0.013%

    No Known Activations