© 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. 4-RES-JB
    11. 10624
    Prev
    Next
    INDEX
    Explanations

    web URLs for additional information or resources

    oai_token-act-pair · gpt-3.5-turbo

    URLs and web links

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

    No Comments

    Negative Logits
     Morse
    -0.69
    axy
    -0.64
    rons
    -0.63
    åŃIJ
    -0.63
    NetMessage
    -0.63
    doms
    -0.62
    oslov
    -0.62
     Sakuya
    -0.62
    ļé
    -0.60
     Paradise
    -0.60
    POSITIVE LOGITS
    ://
    1.41
    natureconservancy
    1.08
    :/
    0.92
     www
    0.83
    archive
    0.78
     https
    0.77
    docs
    0.75
     http
    0.73
     Username
    0.68
    HTTP
    0.68
    Activations Density 0.010%

    No Known Activations