© 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. 3738
    Prev
    Next
    INDEX
    Explanations

    keywords related to technology, particularly computer brands like Lenovo

    oai_token-act-pair · gpt-3.5-turbo

    names of brands and individuals associated with technology and electronics

    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
    terday
    -0.88
    gers
    -0.85
    hog
    -0.83
    ãĤ·ãĥ£
    -0.82
    gee
    -0.78
    bucks
    -0.78
    ãĤ¿
    -0.75
    alez
    -0.74
    lein
    -0.73
    pee
    -0.73
    POSITIVE LOGITS
    earance
    0.72
     SEAL
    0.68
    ovember
    0.68
     Lumpur
    0.67
    ersen
    0.65
     reconc
    0.65
    ouncing
    0.64
    agate
    0.64
    owship
    0.64
    piracy
    0.64
    Activations Density 0.040%

    No Known Activations