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. 12-RES-JB
    6. 14683
    Prev
    Next
    INDEX
    Explanations

    locations and activities within a structured space

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot

    instances of personal experiences and daily activities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 12-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.hook_resid_post
    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_post
    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
     prominently
    -0.90
     secondly
    -0.80
    ."[
    -0.77
    .''.
    -0.77
     vou
    -0.75
    worthiness
    -0.74
     âĢ
    -0.73
     âĢķ
    -0.71
    .�
    -0.70
     furthermore
    -0.68
    POSITIVE LOGITS
     commute
    0.91
     laptop
    0.91
     podcasts
    0.87
     insomnia
    0.84
     caffe
    0.84
     couch
    0.82
     treadmill
    0.81
     blogging
    0.80
    cheat
    0.80
     MacBook
    0.79
    Activations Density 0.471%

    No Known Activations