© 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. 0-RES-JB
    11. 1585
    Prev
    Next
    INDEX
    Explanations

    phrases mentioning specific town names

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "town" and its variations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    iferation
    -0.78
    rils
    -0.64
    oeuv
    -0.63
    ister
    -0.62
    ensitive
    -0.61
     Attribution
    -0.61
    dn
    -0.59
    Sources
    -0.59
     Kissinger
    -0.58
    erves
    -0.58
    POSITIVE LOGITS
     town
    3.76
     Town
    2.36
     towns
    2.35
    Town
    2.09
    town
    2.01
     village
    2.00
     city
    1.89
     township
    1.82
     suburb
    1.66
     municipality
    1.56
    Activations Density 0.018%

    No Known Activations