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. 6653
    Prev
    Next
    INDEX
    Explanations

    dates and locations in a specific format

    oai_token-act-pair · gpt-3.5-turbo

    dates and locations of events, likely related to concerts or festivals

    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
     blackmail
    -0.82
     antit
    -0.79
     anthrop
    -0.78
     veter
    -0.78
     scrap
    -0.77
     cens
    -0.77
     antiv
    -0.75
     reprodu
    -0.74
     buck
    -0.74
     fled
    -0.74
    POSITIVE LOGITS
    Tickets
    1.25
    Saturday
    1.08
    Champ
    1.03
    Events
    1.02
    Week
    1.02
    Particip
    1.01
    CAST
    1.01
    Sunday
    0.99
    Friday
    0.99
    Includes
    0.98
    Activations Density 0.122%

    No Known Activations