© 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. 2991
    Prev
    Next
    INDEX
    Explanations

    terms related to file extensions

    oai_token-act-pair · gpt-3.5-turbo

    references to extensions or modifications in various contexts

    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
     sharks
    -0.79
     wool
    -0.67
     shark
    -0.67
    Reviewer
    -0.66
     traveller
    -0.64
    iard
    -0.64
     eye
    -0.62
    folk
    -0.61
     faces
    -0.61
     Sawyer
    -0.60
    POSITIVE LOGITS
    ension
    1.64
    racted
    1.61
    raction
    1.60
    ensions
    1.55
    ract
    1.52
    ensive
    1.52
    inction
    1.48
    ended
    1.47
    ortion
    1.44
    inct
    1.42
    Activations Density 0.017%

    No Known Activations