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

    Neuronpedia

    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. 4-RES-JB
    11. 605
    Prev
    Next
    INDEX
    Explanations

    words related to rendering or interpretations

    oai_token-act-pair · gpt-3.5-turbo

    references to the concept of "rendition" and associated terms

    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
    gamer
    -0.92
    lifting
    -0.73
    verage
    -0.72
    ulative
    -0.71
    peria
    -0.69
    nuts
    -0.66
    BC
    -0.64
    ä
    -0.64
    train
    -0.63
    QB
    -0.62
    POSITIVE LOGITS
    ezvous
    1.27
    anqu
    0.92
     rend
    0.89
    ouble
    0.83
    ROR
    0.81
    ivals
    0.80
    alis
    0.77
    emonium
    0.77
    escription
    0.75
    itory
    0.75
    Activations Density 0.020%

    No Known Activations