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. 775
    Prev
    Next
    INDEX
    Explanations

    the name "Karl"

    oai_token-act-pair · gpt-3.5-turbo

    mentions of a specific name or term related to a notable individual

    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
     Zeus
    -0.82
     mosaic
    -0.77
     elevation
    -0.69
     diff
    -0.69
     signed
    -0.65
     success
    -0.63
     clinch
    -0.63
     Photoshop
    -0.61
     below
    -0.60
     diffusion
    -0.60
    POSITIVE LOGITS
    arl
    4.51
    arry
    1.19
    arling
    1.18
    arb
    1.16
    arc
    1.15
    arn
    1.07
    arr
    1.07
    arp
    1.05
    sylv
    1.03
    atel
    1.02
    Activations Density 0.010%

    No Known Activations