© 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. 22102
    Prev
    Next
    INDEX
    Explanations

    prominent individuals or professionals in various fields

    oai_token-act-pair · gpt-3.5-turbo

    terms related to roles or professions in media and politics

    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
    crew
    -0.78
    ickle
    -0.78
    word
    -0.77
    aber
    -0.76
    rought
    -0.75
    cale
    -0.73
     helicop
    -0.70
    ainer
    -0.70
    iggurat
    -0.70
    perm
    -0.70
    POSITIVE LOGITS
     extraord
    1.07
     Shaun
    0.90
     Erik
    0.82
     Laura
    0.79
     Stephen
    0.79
     Khalid
    0.78
     Jed
    0.77
     Andrew
    0.77
     Nathan
    0.77
     Vic
    0.76
    Activations Density 0.345%

    No Known Activations