© 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. 0-RES-JB
    11. 7696
    Prev
    Next
    INDEX
    Explanations

    words related to the use or application of something

    oai_token-act-pair · gpt-3.5-turbo

    discussions about various applications or 'uses'

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Schultz
    -0.65
     Hampton
    -0.62
     Skywalker
    -0.61
    elman
    -0.60
     ball
    -0.59
     absentee
    -0.57
     Lac
    -0.56
     Ball
    -0.56
     Dunk
    -0.55
     olig
    -0.55
    POSITIVE LOGITS
    uses
    4.86
    used
    2.14
    using
    2.13
    use
    2.08
    usal
    1.58
    USE
    1.53
    us
    1.36
    usions
    1.36
    users
    1.30
    US
    1.27
    Activations Density 0.010%

    No Known Activations