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. 11000
    Prev
    Next
    INDEX
    Explanations

    the name "Sue" or "Wimbledon" in sentences

    oai_token-act-pair · gpt-3.5-turbo

    names of individuals and references to notable figures in context

    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
    edIn
    -0.76
     è£ıè
    -0.74
     redes
    -0.74
     Emir
    -0.66
     moons
    -0.63
     bargain
    -0.60
    Band
    -0.60
    oggle
    -0.60
    ¿½
    -0.59
     docking
    -0.59
    POSITIVE LOGITS
    terness
    1.03
    pe
    0.79
    uh
    0.78
    ibo
    0.77
    ubi
    0.76
    pg
    0.76
    uge
    0.76
    pper
    0.75
    vier
    0.74
    ppe
    0.74
    Activations Density 0.037%

    No Known Activations