© 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. 10947
    Prev
    Next
    INDEX
    Explanations

    the word "pe" followed by a single digit

    oai_token-act-pair · gpt-3.5-turbo

    instances of the substring "pe"

    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
    é¾
    -0.86
    enegger
    -0.70
     nets
    -0.67
    schild
    -0.67
     GOODMAN
    -0.67
     Kirin
    -0.65
    etheless
    -0.63
     guiActiveUnfocused
    -0.63
    worthy
    -0.62
     swirling
    -0.62
    POSITIVE LOGITS
    cific
    1.05
    anut
    1.02
    oples
    0.95
    asant
    0.95
    rer
    0.94
    cies
    0.90
    ller
    0.90
    cial
    0.89
    rers
    0.89
    eps
    0.88
    Activations Density 0.010%

    No Known Activations