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. 8-RES-JB
    6. 4507
    Prev
    Next
    INDEX
    Explanations

    dates and events

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of dates, events, or significant schedules

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     retali
    -0.75
     dissu
    -0.74
     citiz
    -0.72
     ageing
    -0.71
     interference
    -0.66
     favoured
    -0.66
    heit
    -0.65
     harassment
    -0.65
     anonymity
    -0.65
     censorship
    -0.65
    POSITIVE LOGITS
    PHOTOS
    0.93
    Tickets
    0.88
    ³³³³³³³³³³³³³³³³
    0.81
    ³³³
    0.80
     Related
    0.76
    enture
    0.75
    Meanwhile
    0.74
    Prior
    0.74
    Additionally
    0.73
    Fans
    0.71
    Activations Density 0.463%

    No Known Activations