Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 11-RES-JB
    6. 24326
    Prev
    Next
    INDEX
    Explanations

    references to job-related numbers and figures like job losses, job gains, and job cuts

    oai_token-act-pair · gpt-3.5-turbo

    quantitative data related to job statistics and large numbers

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    gradation
    -0.76
    feeding
    -0.73
    ulence
    -0.71
    bara
    -0.71
    alyses
    -0.70
    estine
    -0.68
    Dialogue
    -0.67
    ifice
    -0.66
    Discuss
    -0.65
    ascript
    -0.65
    POSITIVE LOGITS
     hectares
    1.06
     acres
    1.01
     square
    1.01
     sq
    1.01
     pounds
    0.95
     tonnes
    0.95
    +
    0.94
     lbs
    0.89
     people
    0.88
     euros
    0.88
    Activations Density 0.107%

    No Known Activations