© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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. 4997
    Prev
    Next
    INDEX
    Explanations

    generic words or phrases related to various topics such as technology, politics, and entertainment, without a clear specific focus

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "the" and other common articles or pronouns in the text

    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
    emale
    -0.81
    edIn
    -0.76
    Interstitial
    -0.66
     vulner
    -0.65
    ilaterally
    -0.64
     Seym
    -0.63
     ãĤµãĥ¼ãĥĨãĤ£ãĥ¯ãĥ³
    -0.62
    æµ
    -0.62
     horizont
    -0.62
    ©¶æ
    -0.61
    POSITIVE LOGITS
     Coverage
    0.62
    CRIPTION
    0.55
     Psy
    0.53
    osures
    0.52
     ROCK
    0.51
     Mars
    0.51
     Mant
    0.51
     largeDownload
    0.50
     Disclosure
    0.50
     Steam
    0.49
    Activations Density 0.809%

    No Known Activations