© 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. 2-RES-JB
    11. 8309
    Prev
    Next
    INDEX
    Explanations

    mentions of cells, specifically T-cell receptors or cell units

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     cumbers
    -0.77
    olulu
    -0.75
     caution
    -0.68
    pez
    -0.64
     Seeking
    -0.64
    lift
    -0.63
    laus
    -0.63
    pled
    -0.62
    umble
    -0.62
     risky
    -0.61
    POSITIVE LOGITS
    ular
    1.17
    estial
    1.00
    icides
    0.92
    ularity
    0.92
    mate
    0.90
    cell
    0.88
    ucci
    0.87
    ade
    0.86
    ades
    0.86
    mates
    0.85
    Activations Density 0.006%

    No Known Activations