Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlogSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    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. 79
    Prev
    Next
    INDEX
    Explanations

    phrases that include three-letter acronyms followed by numbers

    oai_token-act-pair · gpt-3.5-turbo

    references to a specific organization or party, indicated by the acronym "PD."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    the abbreviation "PD"

    oai_token-act-pair · gpt-4-turbo
    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
    hab
    -0.83
    glers
    -0.78
    ppo
    -0.75
    hold
    -0.73
    flies
    -0.72
    bourg
    -0.71
    ãĥĦ
    -0.70
    ãĤ°
    -0.70
    Leary
    -0.69
    ships
    -0.68
    POSITIVE LOGITS
    PD
    1.12
    GF
    0.92
    illon
    0.91
    ouble
    0.86
    iamond
    0.82
    rint
    0.80
    uterte
    0.79
    insula
    0.79
     PD
    0.77
    oodle
    0.75
    Activations Density 0.008%

    No Known Activations