© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 2-RES-JB
    6. 5554
    Prev
    Next
    INDEX
    Explanations

    instances where there is a request to re-enter an email address

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "enter."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    hovah
    -0.71
    illard
    -0.66
     runaway
    -0.64
    Ĭ±
    -0.64
    axter
    -0.64
     leak
    -0.64
    verbs
    -0.63
    ermott
    -0.62
     lofty
    -0.62
     jud
    -0.61
    POSITIVE LOGITS
    prise
    1.61
    prises
    1.47
    tainment
    1.07
    TAIN
    1.01
    enter
    0.95
    prising
    0.86
    ology
    0.84
    itus
    0.84
    taining
    0.83
    idon
    0.77
    Activations Density 0.005%

    No Known Activations