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. 2-RES-JB
    6. 13211
    Prev
    Next
    INDEX
    Explanations

    user profiles indicating when individuals joined an online community or platform

    oai_token-act-pair · gpt-3.5-turbo

    instances of user profile join dates and related metadata

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    andro
    -0.86
    ouf
    -0.80
    othe
    -0.73
    othy
    -0.70
    agos
    -0.70
    ider
    -0.70
    utenberg
    -0.69
    iren
    -0.69
    oped
    -0.68
    bull
    -0.68
    POSITIVE LOGITS
     Joined
    1.41
     Starcraft
    0.84
    Joined
    0.80
     Rankings
    0.80
    ertodd
    0.79
    uates
    0.75
    pedia
    0.75
    Offline
    0.71
    zona
    0.71
    âĸ¬
    0.71
    Activations Density 0.006%

    No Known Activations