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. 3-RES-JB
    6. 7829
    Prev
    Next
    INDEX
    Explanations

    Twitter usernames with some specific pattern or structure

    oai_token-act-pair · gpt-3.5-turbo

    mentions of news organizations and their associated personnel on social media

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ACTIONS
    -0.82
    APTER
    -0.72
     soil
    -0.69
     DRAG
    -0.68
     negatives
    -0.66
     CARD
    -0.65
     ABE
    -0.65
    ï¸
    -0.65
     solvent
    -0.65
     critically
    -0.62
    POSITIVE LOGITS
    _
    0.94
    Blog
    0.94
    yp
    0.90
    pod
    0.86
    brew
    0.81
    qq
    0.78
    neys
    0.77
    NBC
    0.77
    oy
    0.76
    MH
    0.76
    Activations Density 0.191%

    No Known Activations