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. 14359
    Prev
    Next
    INDEX
    Explanations

    phrases related to permission or freedom to act as one desires

    oai_token-act-pair · gpt-3.5-turbo

    expressions of desire or permission

    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
    ricks
    -0.73
    ynski
    -0.72
     Berk
    -0.67
    riot
    -0.64
    errors
    -0.62
    bug
    -0.60
    riots
    -0.58
    utenant
    -0.58
     enthusi
    -0.58
    hero
    -0.57
    POSITIVE LOGITS
     to
    0.71
    urities
    0.69
    GB
    0.65
    edIn
    0.63
     mate
    0.63
     quotas
    0.61
    awaru
    0.61
    htar
    0.60
    uld
    0.60
    atra
    0.58
    Activations Density 0.078%

    No Known Activations