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. 7-RES-JB
    6. 19914
    Prev
    Next
    INDEX
    Explanations

    phrases indicating necessity or high importance

    oai_token-act-pair · gpt-3.5-turbo

    phrases expressing standards, recommendations, or essential items

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    oneliness
    -0.70
    ancies
    -0.68
    apy
    -0.67
    cffff
    -0.66
    amar
    -0.65
    agate
    -0.64
    politics
    -0.63
    ternity
    -0.63
    idine
    -0.63
     Sapp
    -0.63
    POSITIVE LOGITS
     favourite
    0.85
     contender
    0.83
     favorite
    0.83
     recourse
    0.82
     motivating
    0.82
     recommendation
    0.81
     culprit
    0.80
     rallying
    0.79
     priority
    0.78
    Topic
    0.77
    Activations Density 0.366%

    No Known Activations