© 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. 517
    Prev
    Next
    INDEX
    Explanations

    proper nouns containing a specific sequence of letters

    oai_token-act-pair · gpt-3.5-turbo

    variations of the word "homes."

    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
    ingly
    -0.73
    RAW
    -0.72
    ivation
    -0.69
    DEP
    -0.69
    ive
    -0.69
    writers
    -0.67
    achusetts
    -0.66
    sb
    -0.65
     takeoff
    -0.64
    ivated
    -0.64
    POSITIVE LOGITS
    ome
    0.97
    chool
    0.96
    omes
    0.95
    orah
    0.93
    cence
    0.78
    nil
    0.76
    peed
    0.76
    aurus
    0.74
    velt
    0.73
    ktop
    0.71
    Activations Density 0.009%

    No Known Activations