© 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. 2-RES-JB
    11. 356
    Prev
    Next
    INDEX
    Explanations

    words starting with "Ped"

    oai_token-act-pair · gpt-4-turbo

    phrases related to the word "Ped"

    oai_token-act-pair · gpt-3.5-turbo

    references to the word "Ped" or related terms indicating a specific group or activity

    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
    BILITY
    -0.73
    IELD
    -0.73
    FUL
    -0.69
    ORGE
    -0.68
     competitiveness
    -0.67
    UGH
    -0.66
    ======
    -0.65
     fries
    -0.63
    ãĤ¼ãĤ¦ãĤ¹
    -0.63
    ãĥĩãĤ£
    -0.62
    POSITIVE LOGITS
    igree
    1.18
    ersen
    1.03
    agog
    0.95
    iments
    0.94
    regon
    0.90
    erson
    0.89
    aling
    0.89
    onto
    0.88
    iatric
    0.88
    ricks
    0.86
    Activations Density 0.009%

    No Known Activations