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. 10012
    Prev
    Next
    INDEX
    Explanations

    alphanumeric sequences starting with special characters and ending with numbers

    oai_token-act-pair · gpt-3.5-turbo

    specific characters or symbols in the text

    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
     ãĤµãĥ¼ãĥĨãĤ£ãĥ¯ãĥ³
    -0.67
     detached
    -0.61
     Tsuk
    -0.61
    lda
    -0.60
     ejected
    -0.60
     cyan
    -0.60
     metabolic
    -0.60
     jacket
    -0.59
     damaged
    -0.59
     Yam
    -0.59
    POSITIVE LOGITS
    _>
    0.91
    Dialogue
    0.86
    tics
    0.85
    ileaks
    0.85
    ı
    0.85
    ¹
    0.80
    ķ
    0.78
    º
    0.76
    ¬¼
    0.76
    ISIS
    0.75
    Activations Density 0.202%

    No Known Activations