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. 10-RES-JB
    6. 19383
    Prev
    Next
    INDEX
    Explanations

    information related to numbers and statistics

    oai_token-act-pair · gpt-3.5-turbo

    numerical data related to incidents or cases

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     horm
    -0.69
    Appearance
    -0.68
     starve
    -0.65
     belie
    -0.64
    Stretch
    -0.64
    odox
    -0.64
    Scroll
    -0.62
     embr
    -0.61
     scattering
    -0.61
     srfAttach
    -0.60
    POSITIVE LOGITS
     354
    0.74
     287
    0.73
     311
    0.72
     registered
    0.72
     331
    0.72
     last
    0.71
    ross
    0.71
     surveyed
    0.71
     332
    0.70
     nationwide
    0.70
    Activations Density 0.551%

    No Known Activations