Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 4-RES-JB
    6. 23744
    Prev
    Next
    INDEX
    Explanations

    locations or places, specifically with the abbreviation "St."

    oai_token-act-pair · gpt-3.5-turbo

    references to the abbreviation 'St' followed by various numbers, indicating locations or streets

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    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
    EStream
    -0.85
    merce
    -0.78
    hower
    -0.74
     GOODMAN
    -0.74
    ption
    -0.72
    hound
    -0.68
    ļéĨĴ
    -0.68
    ptions
    -0.65
    Enlarge
    -0.65
     booths
    -0.64
    POSITIVE LOGITS
    rict
    1.06
    ills
    1.01
    onew
    0.99
    ocking
    0.99
    amped
    0.97
    amps
    0.96
    alker
    0.96
    ealing
    0.96
    igma
    0.95
    irling
    0.95
    Activations Density 0.026%

    No Known Activations