Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APISteerSAE EvalsBlog/PodcastNEWSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlog/PodcastGitHubSlackTwitterContact
    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. 322
    Prev
    Next
    INDEX
    Explanations

    verbs denoting the beginning or initiation of an action

    oai_token-act-pair · gpt-3.5-turbo

    the infinitive form of verbs, particularly "to" followed by verbs

    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
    enance
    -0.71
    cart
    -0.69
    soDeliveryDate
    -0.66
    afety
    -0.63
     regards
    -0.62
     conveyed
    -0.62
    hent
    -0.60
    lain
    -0.60
    rats
    -0.59
    tips
    -0.59
    POSITIVE LOGITS
     accumulate
    0.90
     negotiate
    0.90
     explore
    0.89
     earn
    0.87
     compensate
    0.87
     climb
    0.87
     fray
    0.86
    ggles
    0.84
     imitate
    0.83
     dismantle
    0.81
    Activations Density 0.053%

    No Known Activations