© 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. 8295
    Prev
    Next
    INDEX
    Explanations

    phrases related to television show schedules, specifically debut dates

    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
     mathemat
    -0.72
    ngth
    -0.64
     peace
    -0.63
    displayText
    -0.61
     ado
    -0.60
     thought
    -0.60
     guilt
    -0.59
     plag
    -0.59
     Tu
    -0.57
     distilled
    -0.57
    POSITIVE LOGITS
    atever
    0.77
    herent
    0.74
    ven
    0.74
    ascript
    0.74
     bystand
    0.71
    azines
    0.71
    arent
    0.69
    imov
    0.68
    arah
    0.68
    cart
    0.68
    Activations Density 0.000%

    No Known Activations