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. 16994
    Prev
    Next
    INDEX
    Explanations

    verbs indicating future actions or intentions

    oai_token-act-pair · gpt-3.5-turbo

    expressions of intentions or future actions

    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
    int
    -0.72
    weed
    -0.70
    idge
    -0.68
    aff
    -0.65
    asions
    -0.65
     Kush
    -0.63
    asive
    -0.63
    engu
    -0.62
    ammy
    -0.61
    ãĢIJ
    -0.61
    POSITIVE LOGITS
     Parenthood
    1.01
    paren
    0.84
     accordingly
    0.76
     meals
    0.71
     Plans
    0.70
     pregnancies
    0.68
     gestation
    0.66
     plans
    0.65
     vacations
    0.65
     trips
    0.65
    Activations Density 0.039%

    No Known Activations