© 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. 4522
    Prev
    Next
    INDEX
    Explanations

    specific instructions or details related to a particular topic

    oai_token-act-pair · gpt-3.5-turbo

    phrases that indicate the availability of additional information or resources

    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
    igr
    -0.75
    doms
    -0.73
    pour
    -0.71
    asha
    -0.71
    conn
    -0.71
    ACTED
    -0.70
    eat
    -0.70
    `
    -0.69
    uan
    -0.69
    ociation
    -0.68
    POSITIVE LOGITS
     details
    1.38
     clarification
    1.17
     more
    1.12
     specifics
    1.12
     directions
    1.10
     info
    1.09
     further
    1.07
     instructions
    1.06
     answers
    1.04
     inspiration
    0.99
    Activations Density 0.080%

    No Known Activations