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. 5-RES-JB
    6. 16575
    Prev
    Next
    INDEX
    Explanations

    verbs related to initiating or starting actions or processes

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to the initiation or commencement of actions or processes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 5-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    5
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    quickShipAvailable
    -0.69
    pedia
    -0.64
    yssey
    -0.62
    phy
    -0.59
    ided
    -0.59
    orie
    -0.57
     wrought
    -0.57
     annexed
    -0.56
    pert
    -0.56
     Bowl
    -0.55
    POSITIVE LOGITS
     anew
    0.97
    ezvous
    0.77
    OURCE
    0.74
    TAIN
    0.74
    ione
    0.68
    ners
    0.67
    starting
    0.66
    uce
    0.64
    odcast
    0.64
    strap
    0.64
    Activations Density 0.058%

    No Known Activations