© 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. 471
    Prev
    Next
    INDEX
    Explanations

    terms related to decision-making and choices

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the name "Cho."

    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
    doors
    -0.85
    night
    -0.74
    master
    -0.68
    nings
    -0.66
    vae
    -0.64
     EntityItem
    -0.64
     IMAGES
    -0.62
    system
    -0.62
    Reloaded
    -0.62
    QUIRE
    -0.61
    POSITIVE LOGITS
    osing
    1.11
    ices
    1.05
    pper
    1.04
    oser
    1.04
    ppy
    0.88
    pped
    0.88
    oldown
    0.83
    icer
    0.82
    osen
    0.82
    iral
    0.80
    Activations Density 0.010%

    No Known Activations