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

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 8-RES-JB
    6. 16265
    Prev
    Next
    INDEX
    Explanations

    terms related to amputations

    oai_token-act-pair · gpt-3.5-turbo

    the presence of the word "ute" and its variations, indicating a focus on a specific suffix or terminology

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    awaru
    -0.85
    kell
    -0.76
    psons
    -0.72
     challeng
    -0.69
    terness
    -0.68
    abeth
    -0.66
    anco
    -0.65
     hig
    -0.65
    hips
    -0.65
    idates
    -0.65
    POSITIVE LOGITS
    anu
    0.84
    culosis
    0.80
    vich
    0.77
    xt
    0.75
    urs
    0.75
    lled
    0.74
    anamo
    0.74
     cout
    0.73
     Clause
    0.70
    mble
    0.70
    Activations Density 0.058%

    No Known Activations