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

    Neuronpedia

    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. 7138
    Prev
    Next
    INDEX
    Explanations

    phrases related to technology and community feedback

    oai_token-act-pair · gpt-3.5-turbo

    mentions of retro-related themes or trends in various contexts

    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
    —
    -0.81
    )—
    -0.79
    "—
    -0.69
    —"
    -0.67
    ,—
    -0.67
     Rodham
    -0.66
    .—
    -0.65
    ensical
    -0.65
    ,
    -0.64
    enance
    -0.62
    POSITIVE LOGITS
     thats
    1.16
     hence
    1.10
     ie
    1.10
     whilst
    1.03
     whereas
    1.02
     haha
    1.02
     namely
    1.00
    but
    1.00
     luckily
    0.99
     BUT
    0.98
    Activations Density 0.496%

    No Known Activations