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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 11-RES-JB
    6. 8115
    Prev
    Next
    INDEX
    Explanations

    words related to arguing or conflicts

    oai_token-act-pair · gpt-3.5-turbo

    words that start with the letter 'b'

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     SPD
    -0.64
     Grave
    -0.62
     inhal
    -0.61
    Released
    -0.59
     glow
    -0.58
     Pulse
    -0.58
     Pug
    -0.56
     oblig
    -0.56
     Pharaoh
    -0.56
     Trib
    -0.55
    POSITIVE LOGITS
    ibli
    1.42
    antam
    1.29
    ibliography
    1.28
    arge
    1.23
    rawn
    1.19
    azaar
    1.19
    illet
    1.16
    raid
    1.16
    razil
    1.16
    ordered
    1.16
    Activations Density 0.027%

    No Known Activations