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. 5609
    Prev
    Next
    INDEX
    Explanations

    website URLs ending with .com

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the domain "com", indicating a focus on commercial or website-related references

    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
     governors
    -0.72
     Balt
    -0.67
     bullies
    -0.65
     burgl
    -0.65
     progress
    -0.64
     robbers
    -0.63
     cuts
    -0.62
     Goldberg
    -0.61
     cosmetic
    -0.60
     proced
    -0.59
    POSITIVE LOGITS
    /?
    0.96
    biz
    0.88
    lisher
    0.88
    nw
    0.87
    pleted
    0.87
    pletion
    0.86
    nl
    0.85
    psons
    0.85
    lishing
    0.84
    ibaba
    0.82
    Activations Density 0.031%

    No Known Activations