© 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. 527
    Prev
    Next
    INDEX
    Explanations

    proper nouns or names of people, places, or events

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "became."

    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
    inarily
    -0.76
    inately
    -0.72
    oning
    -0.71
    ramid
    -0.69
    alian
    -0.68
    been
    -0.67
    enger
    -0.64
    atching
    -0.64
    orney
    -0.63
    otropic
    -0.62
    POSITIVE LOGITS
     accustomed
    0.89
     entangled
    0.87
     extinct
    0.84
     embroiled
    0.83
    oslav
    0.82
     acquainted
    0.79
     undone
    0.76
     disillusion
    0.75
    nces
    0.74
    ATURES
    0.73
    Activations Density 0.046%

    No Known Activations