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. 10-RES-JB
    6. 16768
    Prev
    Next
    INDEX
    Explanations

    proper nouns related to grocery stores

    oai_token-act-pair · gpt-3.5-turbo

    variations of the word "groovy" in different contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     PDT
    -0.64
     gulf
    -0.63
     innocence
    -0.62
     duly
    -0.61
     descendant
    -0.60
     CPC
    -0.59
    UAL
    -0.58
     apr
    -0.58
    IDENT
    -0.58
     proceedings
    -0.58
    POSITIVE LOGITS
    tesque
    1.51
    ovy
    1.47
    cery
    1.31
    tto
    1.28
    ove
    1.21
    ggy
    1.21
    veland
    1.15
    tty
    1.10
    ves
    1.05
    cers
    1.04
    Activations Density 0.021%

    No Known Activations