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. 19040
    Prev
    Next
    INDEX
    Explanations

    phrases related to exceptional quality or status

    oai_token-act-pair · gpt-3.5-turbo

    references to classifications related to quality or status, specifically 'world-class'

    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
    pty
    -0.74
    sbm
    -0.71
     Ezek
    -0.65
    foreseen
    -0.64
     wit
    -0.64
    HUD
    -0.64
     Grimes
    -0.64
    OPLE
    -0.64
    arty
    -0.63
    vas
    -0.60
    POSITIVE LOGITS
    ifications
    1.17
    ifiers
    1.00
    ifying
    0.99
    ified
    0.99
    ification
    0.98
    ifiable
    0.88
    ifier
    0.87
    mate
    0.87
    ify
    0.86
    smanship
    0.86
    Activations Density 0.016%

    No Known Activations