© 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. 10-RES-JB
    11. 3175
    Prev
    Next
    INDEX
    Explanations

    phrases mentioning academic journals and institutions

    oai_token-act-pair · gpt-3.5-turbo

    references to academic institutions or journals

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    agascar
    -0.68
     piles
    -0.67
     crate
    -0.66
    bnb
    -0.65
    brush
    -0.65
    wolves
    -0.64
    channelAvailability
    -0.62
    forth
    -0.62
     residue
    -0.61
     haze
    -0.61
    POSITIVE LOGITS
     Sciences
    1.27
     Arts
    1.16
     Science
    1.01
     Pediatrics
    0.91
     Letters
    0.83
     Veterinary
    0.82
     Engineering
    0.79
     Scientists
    0.77
     Literature
    0.75
     arts
    0.75
    Activations Density 0.050%

    No Known Activations