© 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. 7088
    Prev
    Next
    INDEX
    Explanations

    names of people or characters

    oai_token-act-pair · gpt-3.5-turbo

    references to specific individuals and a theme of apathy

    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
    ieri
    -0.72
    amins
    -0.71
     skelet
    -0.70
    nikov
    -0.69
    Assembly
    -0.65
    ARM
    -0.65
    oter
    -0.65
     Citiz
    -0.64
    assic
    -0.63
     synagogue
    -0.63
    POSITIVE LOGITS
    ysis
    0.79
    hammad
    0.76
     actionGroup
    0.75
    Pg
    0.72
    fw
    0.69
    vt
    0.69
    milo
    0.66
    ei
    0.66
    fp
    0.66
    cules
    0.65
    Activations Density 0.031%

    No Known Activations