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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlog/PodcastSlackPrivacy & 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. 24076
    Prev
    Next
    INDEX
    Explanations

    mentions of hunger

    oai_token-act-pair · gpt-3.5-turbo

    references to hunger or being hungry

    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
    idine
    -0.86
     CLSID
    -0.81
    Downloadha
    -0.78
    ioxide
    -0.71
    perty
    -0.69
     Offic
    -0.68
    BuyableInstoreAndOnline
    -0.68
     patented
    -0.67
    DCS
    -0.67
    istically
    -0.66
    POSITIVE LOGITS
     hungry
    0.97
     meals
    0.96
     ghosts
    0.90
    ness
    0.87
     Hungry
    0.81
     thirsty
    0.78
     starving
    0.77
    iesta
    0.75
     crocod
    0.73
    ening
    0.73
    Activations Density 0.016%

    No Known Activations