© 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. 3-RES-JB
    11. 12336
    Prev
    Next
    INDEX
    Explanations

    mentions of interviews and discussions

    oai_token-act-pair · gpt-3.5-turbo

    references to discussions or interviews that involve formal settings and panels

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    wikipedia
    -0.70
     porous
    -0.63
     interpol
    -0.63
    rendered
    -0.61
     guessed
    -0.61
     proportion
    -0.60
    alties
    -0.60
     graph
    -0.59
     factors
    -0.59
    ¤
    -0.59
    POSITIVE LOGITS
     festivities
    0.81
     session
    0.80
    isode
    0.79
    icles
    0.78
     Tues
    0.77
     unveiling
    0.75
     commencement
    0.73
    éĹ
    0.72
     presentations
    0.71
    Sund
    0.71
    Activations Density 0.513%

    No Known Activations