© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 10-RES-JB
    11. 4324
    Prev
    Next
    INDEX
    Explanations

    email-related terms and phrases

    oai_token-act-pair · gpt-3.5-turbo

    phrases urging action or subscription related to news updates

    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
     defe
    -0.64
     Pigs
    -0.64
     Templar
    -0.59
     Mercenary
    -0.56
     Stain
    -0.56
     tou
    -0.56
     Gaw
    -0.55
     somew
    -0.55
     pig
    -0.54
     Ai
    -0.54
    POSITIVE LOGITS
    uters
    0.71
     Kavanaugh
    0.68
    Trend
    0.65
    heast
    0.63
     Breaking
    0.62
    Balt
    0.62
    isode
    0.61
    20439
    0.59
    cloneembedreportprint
    0.58
     Subscribe
    0.58
    Activations Density 0.013%

    No Known Activations