© 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 EvalsExportsinterp-engineNEWAPI 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. 19138
    Prev
    Next
    INDEX
    Explanations

    phrases related to location or geography

    oai_token-act-pair · gpt-3.5-turbo

    the word "surrounding" and its usage in various 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
     WARN
    -0.70
    iasis
    -0.67
    Bay
    -0.67
    hum
    -0.65
    ope
    -0.63
    士
    -0.62
    deal
    -0.62
    chance
    -0.61
    hist
    -0.61
    _-
    -0.61
    POSITIVE LOGITS
     surrounding
    0.86
    cules
    0.80
    rils
    0.73
    lord
    0.68
     surrounds
    0.66
    tones
    0.65
    ãħĭ
    0.63
    ivating
    0.62
     jurisdictions
    0.62
    atform
    0.61
    Activations Density 0.007%

    No Known Activations