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. 1457
    Prev
    Next
    INDEX
    Explanations

    mentions of events, organizations, and places related to the term "Fair"

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "Fair."

    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
    OPLE
    -0.79
    auri
    -0.66
     Uriel
    -0.66
     heck
    -0.65
    imum
    -0.65
     bottleneck
    -0.64
    hent
    -0.61
    ngth
    -0.59
     Reincarnated
    -0.59
     extrad
    -0.58
    POSITIVE LOGITS
    grounds
    1.43
    banks
    1.06
    fair
    1.04
    ground
    1.00
    child
    0.98
    Ĥª
    0.84
    yt
    0.83
    places
    0.82
    bread
    0.81
    trade
    0.78
    Activations Density 0.012%

    No Known Activations