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. 2189
    Prev
    Next
    INDEX
    Explanations

    action verbs that involve some level of effort or achievement

    oai_token-act-pair · gpt-3.5-turbo

    actions associated with tasks, obligations, or responsibilities

    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
    DragonMagazine
    -0.72
    ItemTracker
    -0.61
    soDeliveryDate
    -0.56
    blogspot
    -0.56
    itcher
    -0.55
    xtap
    -0.54
    likely
    -0.54
    pmwiki
    -0.53
    uploads
    -0.53
     Nos
    -0.52
    POSITIVE LOGITS
     oneself
    0.89
    uate
    0.85
     them
    0.77
    enance
    0.75
    igate
    0.73
    urate
    0.72
     him
    0.70
    itate
    0.70
     meaningful
    0.66
    ISE
    0.65
    Activations Density 0.623%

    No Known Activations