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. 2-RES-JB
    6. 24508
    Prev
    Next
    INDEX
    Explanations

    the name "Dykes" in different contexts

    oai_token-act-pair · gpt-3.5-turbo

    references to "Dy" and "dy" as it relates to a recurring topic or subject matter

    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
    å§«
    -0.81
    IZE
    -0.79
    代
    -0.73
    ãĤĤ
    -0.71
    ãģĤ
    -0.70
    sburgh
    -0.68
    oice
    -0.67
    rawdownloadcloneembedreportprint
    -0.67
    士
    -0.67
    insula
    -0.67
    POSITIVE LOGITS
     Dy
    1.08
    gradation
    0.94
    rell
    0.84
     dy
    0.84
    nec
    0.83
    dy
    0.82
    stop
    0.78
    ritch
    0.77
    sty
    0.77
    adic
    0.76
    Activations Density 0.008%

    No Known Activations