© 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. 3-RES-JB
    11. 3759
    Prev
    Next
    INDEX
    Explanations

    names of individuals and possibly places

    oai_token-act-pair · gpt-3.5-turbo

    names of individuals or notable people

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     corrid
    -0.73
    ccording
    -0.68
     cyt
    -0.67
     swollen
    -0.66
     disparate
    -0.65
     citiz
    -0.65
     deadliest
    -0.64
     unfavorable
    -0.63
     pathological
    -0.63
     Palestin
    -0.62
    POSITIVE LOGITS
    igham
    0.89
     Jr
    0.86
    rand
    0.82
    zynski
    0.81
    chuk
    0.81
    baum
    0.81
    strom
    0.80
    gaard
    0.79
    zinski
    0.79
    ansky
    0.79
    Activations Density 0.265%

    No Known Activations