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. 15776
    Prev
    Next
    INDEX
    Explanations

    phrases related to textual content being old, inspired by someone, a part of a larger piece, or reproduced with permission

    oai_token-act-pair · gpt-3.5-turbo

    statements about the age or status of an article

    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
     looms
    -0.80
     Temper
    -0.69
    selves
    -0.66
     Maid
    -0.65
     headaches
    -0.64
    auga
    -0.64
     individuality
    -0.63
     ghosts
    -0.63
     looming
    -0.62
     hordes
    -0.61
    POSITIVE LOGITS
     updated
    0.75
     archived
    0.73
    Ĥ¬
    0.72
    english
    0.71
     reviewed
    0.70
     reproduced
    0.68
     sponsored
    0.68
    review
    0.67
     reprinted
    0.67
     incomplete
    0.67
    Activations Density 0.121%

    No Known Activations