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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 486
    Prev
    Next
    INDEX
    Explanations

    mentions or references to elephants

    oai_token-act-pair · gpt-3.5-turbo

    references to elephants

    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
    sburgh
    -0.85
     Kenobi
    -0.77
    aldehyde
    -0.73
     Fargo
    -0.72
    raints
    -0.70
     Kislyak
    -0.67
     Kendall
    -0.66
    enegger
    -0.66
    DERR
    -0.65
     Keane
    -0.65
    POSITIVE LOGITS
    venth
    1.37
    phant
    1.16
    oton
    1.02
    fter
    0.94
    phies
    0.90
    ven
    0.89
    lect
    0.82
    ighth
    0.82
    reon
    0.81
    ught
    0.80
    Activations Density 0.011%

    No Known Activations