© 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. 38
    Prev
    Next
    INDEX
    Explanations

    phrases indicating affiliation or inclusion

    oai_token-act-pair · gpt-3.5-turbo

    instances where "of" is used to indicate relationships or connections between various subjects or concepts

    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
    acs
    -0.72
     viol
    -0.68
    SCP
    -0.65
    dayName
    -0.62
     pestic
    -0.62
    reys
    -0.61
     conduc
    -0.60
     spiders
    -0.60
     pests
    -0.59
     chimpanzees
    -0.58
    POSITIVE LOGITS
     course
    0.73
     Scouting
    0.68
    course
    0.66
     the
    0.64
    arching
    0.64
    vention
    0.63
    agall
    0.63
    itect
    0.62
    ership
    0.61
     GDP
    0.61
    Activations Density 0.103%

    No Known Activations