© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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. 11-RES-JB
    11. 14868
    Prev
    Next
    INDEX
    Explanations

    comparisons or contrasts between different values or quantities

    oai_token-act-pair · gpt-3.5-turbo

    comparisons between statistical values or data points

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    authorized
    -0.62
    adia
    -0.59
    =-=-=-=-=-=-=-=-
    -0.56
    dar
    -0.55
    arious
    -0.55
    aqu
    -0.54
    ilitating
    -0.53
    STAR
    -0.53
    mes
    -0.53
    phia
    -0.52
    POSITIVE LOGITS
     to
    0.96
     favorably
    0.96
     with
    0.84
     favour
    0.81
     thereto
    0.79
    icut
    0.77
     unto
    0.69
     sharply
    0.68
     compared
    0.68
    to
    0.67
    Activations Density 0.042%

    No Known Activations