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. 9735
    Prev
    Next
    INDEX
    Explanations

    dates represented in a specific format, possibly related to historical events

    oai_token-act-pair · gpt-3.5-turbo

    numerical data and statistics related to specific years

    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
    pora
    -0.75
    aminer
    -0.73
    heed
    -0.70
    iants
    -0.69
    ogical
    -0.69
    anguage
    -0.68
     backfield
    -0.66
    arious
    -0.66
    ité
    -0.65
    enture
    -0.65
    POSITIVE LOGITS
    âĸĪâĸĪ
    1.03
    61
    0.93
    08
    0.92
    07
    0.89
    09
    0.88
    05
    0.88
    06
    0.88
    04
    0.86
    03
    0.86
    th
    0.86
    Activations Density 0.040%

    No Known Activations