© 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. 2-RES-JB
    11. 12920
    Prev
    Next
    INDEX
    Explanations

    proper nouns of well-known individuals or entities

    oai_token-act-pair · gpt-3.5-turbo

    instances of the term "well-known" and its variations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    otom
    -0.77
    cair
    -0.70
    ureau
    -0.69
    otrop
    -0.67
     Cancel
    -0.66
    ©¶æ
    -0.65
    CAP
    -0.64
    assies
    -0.63
    ander
    -0.62
    aman
    -0.61
    POSITIVE LOGITS
    theless
    0.92
    tenance
    0.88
    Initialized
    0.82
    stood
    0.80
    edly
    0.72
    favorite
    0.67
    Voice
    0.67
    dated
    0.66
    iating
    0.66
    landish
    0.65
    Activations Density 0.083%

    No Known Activations