© 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. 0-RES-JB
    11. 23227
    Prev
    Next
    INDEX
    Explanations

    mentions of the name "Oran" and "Van" in a document

    oai_token-act-pair · gpt-3.5-turbo

    references to specific individuals and concepts related to improvements or positive changes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Curiosity
    -0.69
     stride
    -0.66
     Tart
    -0.64
     pits
    -0.63
     energies
    -0.61
    д
    -0.59
     Kung
    -0.59
    gered
    -0.59
     Godzilla
    -0.59
     vigilance
    -0.59
    POSITIVE LOGITS
    oran
    2.97
    better
    1.98
    Van
    1.54
    agher
    1.18
    âģ
    1.01
    emade
    0.95
    uscript
    0.93
    NBA
    0.91
    NV
    0.85
    nexus
    0.84
    Activations Density 0.056%

    No Known Activations