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. 24212
    Prev
    Next
    INDEX
    Explanations

    references to gaining knowledge or new information through observation or discovery

    oai_token-act-pair · gpt-3.5-turbo

    references to past events and shared experiences

    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
    BuyableInstoreAndOnline
    -1.00
    "))
    -0.90
    ");
    -0.85
    ").
    -0.81
    !",
    -0.79
    !".
    -0.78
    )",
    -0.78
    "},
    -0.76
    ').
    -0.76
     ',
    -0.76
    POSITIVE LOGITS
     somebody
    1.07
     uh
    1.06
    --
    1.00
     basically
    0.99
    Enlarge
    0.97
     sort
    0.97
    ----
    0.96
     everybody
    0.91
    ——
    0.89
     kind
    0.89
    Activations Density 0.865%

    No Known Activations