© 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. 10-RES-JB
    11. 6700
    Prev
    Next
    INDEX
    Explanations

    locations or place names, specifically ones ending in "der" and "der"

    oai_token-act-pair · gpt-3.5-turbo

    references to entities or groups, particularly in a context of comparison or categorization

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ured
    -0.69
     reprodu
    -0.65
    urious
    -0.63
     filib
    -0.62
    urers
    -0.61
     crim
    -0.60
     veter
    -0.58
     Mehran
    -0.57
     showc
    -0.57
    rosse
    -0.55
    POSITIVE LOGITS
    theless
    1.31
    dash
    1.25
    mere
    1.14
    bolt
    1.06
    wise
    0.99
    lust
    0.99
    dale
    0.95
    mia
    0.95
    side
    0.95
    pool
    0.95
    Activations Density 0.086%

    No Known Activations