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. 10-RES-JB
    6. 7385
    Prev
    Next
    INDEX
    Explanations

    comparisons using the word "as"

    oai_token-act-pair · gpt-3.5-turbo

    comparative phrases that emphasize similarity or quality

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    enhagen
    -0.73
    elsen
    -0.71
    wrap
    -0.71
    wire
    -0.70
    venants
    -0.67
    ppo
    -0.64
     Picks
    -0.63
    window
    -0.63
    stadt
    -0.62
     Releases
    -0.62
    POSITIVE LOGITS
     drastic
    1.19
     diverse
    1.18
     complicated
    1.16
     mundane
    1.15
     prestigious
    1.14
     complex
    1.12
     severe
    1.11
     innocuous
    1.11
     profound
    1.11
     egregious
    1.10
    Activations Density 0.170%

    No Known Activations