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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlog/PodcastSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlog/PodcastGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 5-RES-JB
    6. 2233
    Prev
    Next
    INDEX
    Explanations

    statistics or facts about different types of people or populations

    oai_token-act-pair · gpt-3.5-turbo

    references to average individuals and their behaviors or experiences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 5-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    5
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    metadata
    -0.79
     engines
    -0.72
     incorporation
    -0.72
     divisions
    -0.72
    utherland
    -0.70
     deletion
    -0.69
     ingred
    -0.68
     forfeiture
    -0.67
     domains
    -0.66
     arrangements
    -0.66
    POSITIVE LOGITS
     who
    1.00
    who
    0.83
     dared
    0.73
     farmer
    0.73
     whom
    0.72
     believer
    0.72
     whose
    0.72
    athon
    0.71
    hawk
    0.71
     thinks
    0.69
    Activations Density 0.575%

    No Known Activations