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. 23348
    Prev
    Next
    INDEX
    Explanations

    names of individuals, particularly surnames

    oai_token-act-pair · gpt-3.5-turbo

    names of people and places related to specific individuals

    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
    itcher
    -0.70
    akia
    -0.67
     Twain
    -0.67
    hh
    -0.65
    irts
    -0.63
    ":["
    -0.63
     repayment
    -0.62
    iage
    -0.62
    ika
    -0.61
    ither
    -0.61
    POSITIVE LOGITS
    atech
    0.86
    urses
    0.78
    olls
    0.77
    ursed
    0.74
    aught
    0.74
    agher
    0.73
    acci
    0.71
    onut
    0.71
    ption
    0.70
    rete
    0.70
    Activations Density 0.036%

    No Known Activations