© 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. 3-RES-JB
    11. 1907
    Prev
    Next
    INDEX
    Explanations

    verbs related to taking action or bringing about a change

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "make" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    76561
    -0.69
     Vest
    -0.66
    bour
    -0.62
     scrimmage
    -0.62
    ---------
    -0.62
     Leban
    -0.61
     nurs
    -0.61
     Ging
    -0.58
     Wick
    -0.56
     Suit
    -0.56
    POSITIVE LOGITS
     sure
    1.02
    hift
    1.00
    awaru
    0.89
    ailable
    0.86
    emort
    0.82
    ÄŁ
    0.78
    ebin
    0.77
    itions
    0.75
     landfall
    0.75
    urate
    0.74
    Activations Density 0.147%

    No Known Activations