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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 4-RES-JB
    6. 279
    Prev
    Next
    INDEX
    Explanations

    words related to articles or written text

    oai_token-act-pair · gpt-3.5-turbo

    the end of document markers

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

    No Comments

    Negative Logits
    emale
    -0.68
    ilaterally
    -0.65
    Interstitial
    -0.64
    stood
    -0.59
    akespe
    -0.59
     horizont
    -0.58
     ãĤµãĥ¼ãĥĨãĤ£ãĥ¯ãĥ³
    -0.56
    xxxx
    -0.56
    itud
    -0.55
     helicop
    -0.55
    POSITIVE LOGITS
    zbollah
    0.64
    UTERS
    0.63
    chwitz
    0.60
    ¶
    0.57
    Elsa
    0.57
     largeDownload
    0.57
    Wiki
    0.55
     Mant
    0.54
    ANS
    0.54
     Pos
    0.54
    Activations Density 0.226%

    No Known Activations