© 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. 19864
    Prev
    Next
    INDEX
    Explanations

    phrases related to dining and social events

    oai_token-act-pair · gpt-3.5-turbo

    punctuation marks within a list format

    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
    OME
    -0.63
    ocial
    -0.61
    assian
    -0.59
    itionally
    -0.56
    afety
    -0.56
    uge
    -0.55
    ensed
    -0.55
    utenant
    -0.54
    reated
    -0.54
    oros
    -0.54
    POSITIVE LOGITS
     etc
    1.18
     respectively
    1.00
     albeit
    0.92
    76561
    0.82
    etc
    0.79
     aka
    0.76
    âĵĺ
    0.75
     alas
    0.72
     namely
    0.71
     culminating
    0.69
    Activations Density 1.204%

    No Known Activations