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. 7-RES-JB
    6. 2623
    Prev
    Next
    INDEX
    Explanations

    time and date information within a specific format

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "Posted" followed by a timestamp or date

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    isky
    -0.82
    ivo
    -0.79
    ppard
    -0.78
    fell
    -0.76
    ishi
    -0.74
    finder
    -0.72
    oller
    -0.70
    ibe
    -0.70
    ingly
    -0.70
    ively
    -0.70
    POSITIVE LOGITS
    vertis
    0.71
    itors
    0.70
    monton
    0.68
    MON
    0.67
    Posted
    0.66
     Comments
    0.66
     prominently
    0.62
     Towns
    0.61
     Helpful
    0.60
    erick
    0.59
    Activations Density 0.015%

    No Known Activations