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. 8-RES-JB
    6. 21454
    Prev
    Next
    INDEX
    Explanations

    the word "UR" with varying strengths of activation

    oai_token-act-pair · gpt-3.5-turbo

    words related to the concept of "reputation."

    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
     Unch
    -0.84
    hower
    -0.68
    ACP
    -0.66
     Ultron
    -0.64
     Strauss
    -0.64
     Quart
    -0.63
     Prescott
    -0.63
     Dawkins
    -0.62
     Blank
    -0.62
     Grimes
    -0.60
    POSITIVE LOGITS
    posed
    1.19
    posing
    1.09
    pose
    1.01
    atives
    0.97
    lishing
    0.94
    rect
    0.90
    poses
    0.88
    ateurs
    0.86
    tenance
    0.86
    ricular
    0.85
    Activations Density 0.043%

    No Known Activations