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. 16768
    Prev
    Next
    INDEX
    Explanations

    phrases related to research, analysis, and studies

    oai_token-act-pair · gpt-3.5-turbo

    personal pronouns and their usage in context

    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
     Lumpur
    -0.66
    Cooldown
    -0.65
     Extension
    -0.64
    Exit
    -0.63
    pite
    -0.62
    edIn
    -0.60
     Directions
    -0.59
     Vanity
    -0.59
    growth
    -0.59
     Framework
    -0.59
    POSITIVE LOGITS
    'll
    0.93
     encountered
    0.89
     showcased
    0.89
     explored
    0.88
     witnessed
    0.82
     pitted
    0.81
     experimented
    0.81
     demonstrated
    0.80
     encount
    0.80
     interacted
    0.79
    Activations Density 0.248%

    No Known Activations