© 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. 2686
    Prev
    Next
    INDEX
    Explanations

    references to the presence or absence of entities or objects in a specific context

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "present" indicating attendance or existence

    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
    STAR
    -0.77
    aird
    -0.75
    gee
    -0.72
    edes
    -0.68
    jet
    -0.68
    mys
    -0.67
    illet
    -0.67
    jar
    -0.67
    reg
    -0.66
    Leod
    -0.65
    POSITIVE LOGITS
    encing
    0.92
    present
    0.91
    eering
    0.89
     Present
    0.89
    Present
    0.78
    iment
    0.74
     Danger
    0.73
    ENTS
    0.72
    iments
    0.70
    ocument
    0.69
    Activations Density 0.012%

    No Known Activations