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. 10-RES-JB
    6. 9484
    Prev
    Next
    INDEX
    Explanations

    mentions of names

    oai_token-act-pair · gpt-3.5-turbo

    references to the name "Bobby."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Leilan
    -0.75
    gypt
    -0.65
    perse
    -0.64
    ebook
    -0.63
    PF
    -0.62
     Machina
    -0.62
    finding
    -0.60
    cele
    -0.59
     vetting
    -0.58
     legion
    -0.58
    POSITIVE LOGITS
     Jindal
    1.05
    rick
    0.89
    ging
    0.89
     Fischer
    0.88
     McGee
    0.83
     Petr
    0.82
    rics
    0.82
     Sands
    0.81
     Eaton
    0.80
     Byrd
    0.80
    Activations Density 0.027%

    No Known Activations