© 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. 652
    Prev
    Next
    INDEX
    Explanations

    words related to seating or placement, particularly in a sports context

    oai_token-act-pair · gpt-3.5-turbo

    references to being on the bench in a sports context

    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
    natureconservancy
    -0.68
    Educ
    -0.68
     Educ
    -0.68
     ISBN
    -0.67
     Autumn
    -0.64
     Breed
    -0.63
    Operation
    -0.62
    alez
    -0.62
     Aval
    -0.61
     Theft
    -0.61
    POSITIVE LOGITS
     bench
    1.09
     benches
    1.03
    warm
    0.77
    iron
    0.72
    ing
    0.72
    lain
    0.70
     warrants
    0.70
     assignments
    0.69
     sergeant
    0.68
    lift
    0.68
    Activations Density 0.007%

    No Known Activations