© 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. 17419
    Prev
    Next
    INDEX
    Explanations

    proper nouns and names related to persons or entities

    oai_token-act-pair · gpt-3.5-turbo

    proper nouns and references to notable individuals and entities

    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
    umbs
    -0.69
    ©¶æ
    -0.68
    tml
    -0.66
    oso
    -0.63
    pires
    -0.63
    rams
    -0.62
    ģĸ
    -0.61
    aughed
    -0.59
    Western
    -0.59
    uristic
    -0.59
    POSITIVE LOGITS
     being
    1.08
     whereabouts
    1.04
     disappearing
    1.03
     becoming
    0.99
     impending
    0.98
     needing
    0.96
    being
    0.94
     deteriorating
    0.92
     finances
    0.91
     looming
    0.90
    Activations Density 0.609%

    No Known Activations