© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 16859
    Prev
    Next
    INDEX
    Explanations

    mentions of proper nouns or specific entities

    oai_token-act-pair · gpt-3.5-turbo

    instances of the character "ľ" and related symbols

    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
    raints
    -0.76
     condem
    -0.75
     apes
    -0.72
     reflex
    -0.68
     deed
    -0.66
     Seym
    -0.66
     unborn
    -0.66
     tort
    -0.65
     hemor
    -0.65
     gist
    -0.65
    POSITIVE LOGITS
    ï¸ı
    1.22
    âĶĢâĶĢ
    1.16
    °
    0.93
    jj
    0.91
    ternity
    0.89
    âĸł
    0.88
    0.88
    âĢł
    0.86
    uthor
    0.86
    ··
    0.85
    Activations Density 0.268%

    No Known Activations