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. 3-RES-JB
    6. 713
    Prev
    Next
    INDEX
    Explanations

    verbs related to staking or claiming something

    oai_token-act-pair · gpt-3.5-turbo

    forms of the verb "stake" and its variations in different contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    catentry
    -0.73
    vernment
    -0.63
    ternity
    -0.61
    irlf
    -0.61
     foresee
    -0.59
    agi
    -0.58
     solicit
    -0.58
     overseen
    -0.57
     ages
    -0.55
     Jinn
    -0.55
    POSITIVE LOGITS
    helm
    0.77
    ngth
    0.74
    warts
    0.71
    ggle
    0.69
    ulent
    0.69
    ffen
    0.68
    ulence
    0.67
     Ahead
    0.67
    osterone
    0.67
    adder
    0.66
    Activations Density 0.053%

    No Known Activations