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. 0-RES-JB
    6. 6008
    Prev
    Next
    INDEX
    Explanations

    words related to the number 'nineteen'

    oai_token-act-pair · gpt-3.5-turbo

    references to age or specific generations

    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
     traff
    -0.79
     rhythm
    -0.65
     Pixel
    -0.63
     Scal
    -0.57
     MAP
    -0.57
     default
    -0.56
     polyg
    -0.56
     domain
    -0.56
     gent
    -0.56
     sculpture
    -0.55
    POSITIVE LOGITS
    een
    4.77
    eenth
    2.05
    eer
    1.65
    eteen
    1.34
    teen
    1.32
    ees
    1.27
    eers
    1.16
    aan
    1.14
    ean
    1.06
    eks
    1.06
    Activations Density 0.009%

    No Known Activations