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. 0-RES-JB
    6. 14077
    Prev
    Next
    INDEX
    Explanations

    references to being honored or celebrated for achievements

    oai_token-act-pair · gpt-3.5-turbo

    references to "Hall of Fame."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     centrally
    -0.74
     slip
    -0.68
     intr
    -0.67
    uter
    -0.67
     vector
    -0.65
     disrupted
    -0.64
    block
    -0.64
     mac
    -0.64
     bol
    -0.63
     dev
    -0.63
    POSITIVE LOGITS
     Fame
    3.92
     fame
    1.84
     Shame
    1.21
     Fam
    1.13
     Famous
    1.05
     notoriety
    1.03
    phies
    1.02
     Excellence
    0.98
     Happiness
    0.98
     renown
    0.97
    Activations Density 0.015%

    No Known Activations