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. 4035
    Prev
    Next
    INDEX
    Explanations

    references to specific locations or people, such as places in Bavaria or the name Calder

    oai_token-act-pair · gpt-3.5-turbo

    references to Bavarian and related geographical or historical contexts

    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
    mington
    -0.79
    ciating
    -0.76
    ually
    -0.66
    ledge
    -0.66
    perse
    -0.66
    natureconservancy
    -0.65
    emouth
    -0.65
     IMAGES
    -0.63
    earchers
    -0.63
    ships
    -0.63
    POSITIVE LOGITS
    illus
    0.86
    ÃĽ
    0.83
     Bav
    0.77
     XVI
    0.72
    nuts
    0.72
    nut
    0.70
    uning
    0.68
     Peninsula
    0.67
    ç
    0.67
    ij
    0.67
    Activations Density 0.030%

    No Known Activations