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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 446
    Prev
    Next
    INDEX
    Explanations

    URLs or web addresses, particularly those starting with "https://t.co/"

    oai_token-act-pair · gpt-4-turbo

    web URLs

    oai_token-act-pair · gpt-3.5-turbo

    URLs and web links

    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
    Ĥİ
    -0.38
     Pwr
    -0.37
    EStream
    -0.37
    NetMessage
    -0.36
    DragonMagazine
    -0.33
     fixme
    -0.32
     ãĤµãĥ¼ãĥĨãĤ£ãĥ¯ãĥ³
    -0.32
     Pastebin
    -0.32
    catentry
    -0.31
     lapt
    -0.30
    POSITIVE LOGITS
    odd
    0.42
    uff
    0.42
    inton
    0.42
    rous
    0.41
    ube
    0.40
    unn
    0.40
    ru
    0.40
    ron
    0.39
    rench
    0.39
    uffed
    0.39
    Activations Density 2.166%

    No Known Activations