© 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. 3729
    Prev
    Next
    INDEX
    Explanations

    words related to retro themes or concepts

    oai_token-act-pair · gpt-3.5-turbo

    references to retro themes or aesthetics

    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
    gow
    -0.74
    avanaugh
    -0.72
    à¨
    -0.69
    holder
    -0.67
    gans
    -0.67
    RAW
    -0.66
    FUL
    -0.66
    illary
    -0.65
    chens
    -0.64
    UGE
    -0.64
    POSITIVE LOGITS
    actively
    1.42
    active
    1.23
    spective
    1.18
     retro
    1.09
    fitted
    1.00
    gradation
    0.97
    spect
    0.94
    fit
    0.94
    spection
    0.93
    fits
    0.91
    Activations Density 0.008%

    No Known Activations