© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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. 9791
    Prev
    Next
    INDEX
    Explanations

    mentions of the term "EP" with different numbers indicating the level of interest

    oai_token-act-pair · gpt-3.5-turbo

    references to extended play (EP) records

    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
     clos
    -0.66
     fir
    -0.65
     Sammy
    -0.64
     marsh
    -0.61
     Kay
    -0.61
     contra
    -0.60
     Shades
    -0.60
     Sud
    -0.59
     clerks
    -0.58
     layouts
    -0.58
    POSITIVE LOGITS
    EP
    4.39
    ep
    1.67
     EP
    1.59
    EC
    1.48
    EM
    1.48
    eps
    1.36
    EMP
    1.29
    EB
    1.24
    EG
    1.23
    IP
    1.22
    Activations Density 0.006%

    No Known Activations