© 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. 10182
    Prev
    Next
    INDEX
    Explanations

    phrases related to specific names, possibly related to fashion and technology

    oai_token-act-pair · gpt-3.5-turbo

    references to specific individuals or brands, particularly in a context related to sports or competition

    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
    ĸļ
    -0.85
    schild
    -0.73
    azeera
    -0.69
     plur
    -0.67
    ources
    -0.66
     GOODMAN
    -0.61
     Spiegel
    -0.61
     Normandy
    -0.61
    pard
    -0.60
    ways
    -0.58
    POSITIVE LOGITS
    ople
    0.72
    jee
    0.71
    ciation
    0.71
    sylvania
    0.70
    sylv
    0.70
    itent
    0.68
    ongyang
    0.68
    asus
    0.67
    γ
    0.67
    ĵĺ
    0.66
    Activations Density 0.721%

    No Known Activations