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. 1-RES-JB
    6. 8354
    Prev
    Next
    INDEX
    Explanations

    verbs related to persistence or perseverance

    oai_token-act-pair · gpt-3.5-turbo

    the concept of persistence in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    avez
    -0.71
    foot
    -0.68
    leans
    -0.67
     GEAR
    -0.67
    ramid
    -0.67
    ammy
    -0.66
    atana
    -0.65
     GOODMAN
    -0.64
    neau
    -0.62
     Deal
    -0.62
    POSITIVE LOGITS
     persisted
    1.23
     persist
    1.12
     persists
    1.09
    ently
    1.02
    enza
    0.92
    ency
    0.81
    rences
    0.77
     unchanged
    0.76
    uates
    0.75
     conclud
    0.75
    Activations Density 0.003%

    No Known Activations