© 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. 13580
    Prev
    Next
    INDEX
    Explanations

    social media posts containing links to external platforms

    oai_token-act-pair · gpt-3.5-turbo

    instances of online content being shared or uploaded

    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
    involved
    -0.63
    natureconservancy
    -0.63
    rats
    -0.60
    roo
    -0.58
    bent
    -0.54
    "},"
    -0.53
     fitt
    -0.53
    iasis
    -0.52
    kj
    -0.51
    olutions
    -0.51
    POSITIVE LOGITS
     by
    1.10
     anonymously
    0.89
     aloud
    0.87
     aback
    0.83
    nesday
    0.82
     exclusively
    0.78
     BY
    0.75
     online
    0.75
     Wednesday
    0.73
     via
    0.72
    Activations Density 0.108%

    No Known Activations