© 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 EvalsExportsinterp-engineNEWAPI 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. 8-RES-JB
    11. 24552
    Prev
    Next
    INDEX
    Explanations

    phrases indicating the start or the type of a new article

    oai_token-act-pair · gpt-3.5-turbo

    references to articles

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Ĭ±
    -0.70
    Lens
    -0.69
    ãĤ¤ãĥĪ
    -0.68
    bats
    -0.62
     Governors
    -0.62
    sed
    -0.62
     Genie
    -0.61
    Tokens
    -0.61
     selves
    -0.60
     Meaning
    -0.59
    POSITIVE LOGITS
     contains
    0.93
     summarizes
    0.93
     assumes
    0.92
     represents
    0.81
     requires
    0.80
    ittee
    0.79
     describes
    0.79
     illustrates
    0.76
     relies
    0.76
     corresponds
    0.76
    Activations Density 0.119%

    No Known Activations