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. 3-RES-JB
    6. 8472
    Prev
    Next
    INDEX
    Explanations

    strings ending in 's' that suggest plural form or possessives

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the letter 's'

    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
    EStream
    -0.72
     preventive
    -0.66
     fuss
    -0.63
     Presidents
    -0.63
     boycot
    -0.63
    SIGN
    -0.63
     GOODMAN
    -0.62
     arming
    -0.62
     adjunct
    -0.61
     indemn
    -0.60
    POSITIVE LOGITS
    omew
    1.02
    ources
    1.02
    kaya
    0.96
    hips
    0.94
    ourced
    0.93
    ometime
    0.92
    essions
    0.91
    ouls
    0.90
    wered
    0.89
    iblings
    0.89
    Activations Density 0.357%

    No Known Activations