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. 6-RES-JB
    6. 18133
    Prev
    Next
    INDEX
    Explanations

    superlatives and terms related to size or importance

    oai_token-act-pair · gpt-3.5-turbo

    superlative forms of adjectives and phrases indicating the highest degree or significance

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    abus
    -0.78
    arth
    -0.76
    uador
    -0.70
     Canaver
    -0.69
     Kuala
    -0.69
    arthy
    -0.66
    ghai
    -0.65
    ocene
    -0.65
     Bundy
    -0.64
     USPS
    -0.63
    POSITIVE LOGITS
     adversary
    0.94
     adversaries
    0.88
    iaries
    0.87
     foray
    0.84
     selves
    0.84
     collaborator
    0.78
     intentions
    0.76
     counterparts
    0.75
     predecessors
    0.74
     outing
    0.73
    Activations Density 0.113%

    No Known Activations