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

    Neuronpedia

    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. 567
    Prev
    Next
    INDEX
    Explanations

    proper nouns or acronyms related to organizations or events

    oai_token-act-pair · gpt-3.5-turbo

    references to the National Cancer Institute or related organizations and terms

    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
    thing
    -0.87
    chest
    -0.77
    loo
    -0.73
    shake
    -0.72
    Magikarp
    -0.71
     mats
    -0.69
    tons
    -0.68
    mania
    -0.67
    Picture
    -0.67
    many
    -0.67
    POSITIVE LOGITS
    urses
    1.07
    ODE
    0.94
    ategor
    0.89
    urrent
    0.88
    NC
    0.85
    ouri
    0.84
    ossus
    0.82
    ADE
    0.80
    onduct
    0.76
     NC
    0.76
    Activations Density 0.007%

    No Known Activations