© 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. 1-RES-JB
    11. 22620
    Prev
    Next
    INDEX
    Explanations

    mentions of the word "Cell" in the context of various subjects or entities

    oai_token-act-pair · gpt-3.5-turbo

    references to scientific journals and cell-related terms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    irted
    -0.97
    itably
    -0.95
    wark
    -0.85
    dding
    -0.74
    iannopoulos
    -0.73
    tesy
    -0.71
    hooting
    -0.71
    irting
    -0.70
     borough
    -0.69
     flagged
    -0.69
    POSITIVE LOGITS
     Cere
    0.88
     Cell
    0.88
     Sensor
    0.86
     Reports
    0.86
     Mechan
    0.85
    onom
    0.83
     Lives
    0.82
    ZI
    0.81
    iris
    0.81
     Effect
    0.81
    Activations Density 0.030%

    No Known Activations