© 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. 4-RES-JB
    11. 1140
    Prev
    Next
    INDEX
    Explanations

    concepts related to limitations and restrictions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    technical terms related to limitations or restrictions

    oai_token-act-pair · gpt-3.5-turbo
    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
    psc
    -0.73
    uni
    -0.72
    hex
    -0.68
    axy
    -0.67
    ocaust
    -0.66
    mberg
    -0.66
    estone
    -0.66
    ************
    -0.66
    hod
    -0.66
    ublic
    -0.64
    POSITIVE LOGITS
     constraints
    1.14
     constraint
    1.08
     constrained
    0.95
     imposed
    0.88
     restraints
    0.85
     dictates
    0.84
     cooker
    0.81
    ellar
    0.80
     Skinner
    0.76
     pressures
    0.75
    Activations Density 0.017%

    No Known Activations