© 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. 9761
    Prev
    Next
    INDEX
    Explanations

    references to a character named Daryl

    oai_token-act-pair · gpt-3.5-turbo

    mentions of specific characters or individuals, particularly the name "Daryl."

    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
    ournal
    -0.84
    odore
    -0.76
    rontal
    -0.75
    ealous
    -0.73
    reme
    -0.69
    pressed
    -0.68
    arrass
    -0.68
    antha
    -0.66
     Fres
    -0.65
    culus
    -0.65
    POSITIVE LOGITS
    banks
    0.83
    igans
    0.76
    IVERS
    0.74
    houses
    0.73
    irling
    0.73
    obyl
    0.72
     Warsaw
    0.68
    stones
    0.68
     Beir
    0.68
    ç«
    0.67
    Activations Density 0.027%

    No Known Activations