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

    Neuronpedia

    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. 1-RES-JB
    11. 3608
    Prev
    Next
    INDEX
    Explanations

    word forms related to the physical concept of area

    oai_token-act-pair · gpt-3.5-turbo

    terms related to "footprint," particularly in ecological or metaphorical contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     doctors
    -0.70
    icum
    -0.70
    ums
    -0.69
    une
    -0.69
    end
    -0.67
    erest
    -0.66
    actionDate
    -0.65
    ending
    -0.64
    acha
    -0.64
    neg
    -0.63
    POSITIVE LOGITS
     footprint
    1.70
     footprints
    1.41
    Þ
    0.77
     teasp
    0.76
     eleph
    0.76
    ãĤ¼ãĤ¦ãĤ¹
    0.74
     prints
    0.73
     multiplier
    0.72
     stump
    0.71
    ãĥ¼ãĥĨãĤ£
    0.71
    Activations Density 0.006%

    No Known Activations