© 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. 10500
    Prev
    Next
    INDEX
    Explanations

    news articles, reports, or related stories

    oai_token-act-pair · gpt-3.5-turbo

    references to related articles or stories

    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
    gran
    -0.64
     truth
    -0.63
     gren
    -0.63
    wagen
    -0.61
    Ò
    -0.59
    osc
    -0.58
    scl
    -0.58
     cryst
    -0.57
    LOD
    -0.57
     shaken
    -0.57
    POSITIVE LOGITS
    esides
    0.79
     Expand
    0.79
     Perspect
    0.74
     Learns
    0.72
     Opinion
    0.69
     Posts
    0.69
     Wear
    0.67
     Articles
    0.67
     Travels
    0.67
     Legislation
    0.65
    Activations Density 0.052%

    No Known Activations