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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlog/PodcastSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlog/PodcastGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 5-RES-JB
    6. 22931
    Prev
    Next
    INDEX
    Explanations

    names or terms related to a specific celebrity or figure (Snoop Dogg)

    oai_token-act-pair · gpt-3.5-turbo

    references to specific characters or figures, particularly those related to "Dog."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 5-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    5
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    idences
    -0.80
    ength
    -0.78
    terday
    -0.71
    CBC
    -0.69
    iflower
    -0.68
     Vaugh
    -0.67
     Lanka
    -0.67
     Sacrament
    -0.63
     intervals
    -0.63
    iversal
    -0.63
    POSITIVE LOGITS
    gers
    1.12
    ger
    1.11
    ging
    1.10
    ged
    1.09
    gart
    1.08
    gie
    1.02
    zag
    1.00
    matic
    0.96
    gin
    0.96
    gy
    0.94
    Activations Density 0.031%

    No Known Activations