© 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. 9-RES-JB
    11. 20774
    Prev
    Next
    INDEX
    Explanations

    responses or lack of responses to requests for comments or information

    oai_token-act-pair · gpt-3.5-turbo

    references to requests for comments

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    tumblr
    -0.69
    animate
    -0.61
     harness
    -0.60
     wre
    -0.59
     visionary
    -0.57
    Untitled
    -0.56
     joints
    -0.55
     Gaw
    -0.55
    ãĤ³
    -0.55
     fasc
    -0.54
    POSITIVE LOGITS
     Jazeera
    0.77
    dozen
    0.72
    ogh
    0.72
    osta
    0.71
     seeking
    0.68
    fax
    0.68
    resso
    0.68
    elf
    0.67
    bush
    0.65
     VIDEOS
    0.65
    Activations Density 0.188%

    No Known Activations