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. 1-RES-JB
    6. 24462
    Prev
    Next
    INDEX
    Explanations

    phrases related to providing support or assistance

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word 'supporting'

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    nown
    -0.76
    elsius
    -0.75
    deal
    -0.75
    Chem
    -0.74
    OPE
    -0.73
    oufl
    -0.72
    ordon
    -0.71
    odor
    -0.69
    kay
    -0.68
    chemy
    -0.68
    POSITIVE LOGITS
     supporting
    1.11
     Supports
    1.05
     supports
    0.96
     Supporting
    0.94
     support
    0.93
    Support
    0.87
     SUPPORT
    0.87
     Supporters
    0.85
    ="#
    0.83
     supporters
    0.80
    Activations Density 0.007%

    No Known Activations