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. 1-RES-JB
    6. 15002
    Prev
    Next
    INDEX
    Explanations

    numerical ratings or evaluations given to various entities

    oai_token-act-pair · gpt-3.5-turbo

    phrases that indicate ratings or evaluations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    vous
    -0.92
     Nou
    -0.82
    ansson
    -0.77
    vas
    -0.76
    adr
    -0.75
    alter
    -0.75
    olding
    -0.73
    nee
    -0.72
    isting
    -0.72
     Alz
    -0.71
    POSITIVE LOGITS
     rated
    1.38
     veter
    1.05
     ratings
    1.04
     rating
    1.04
     unbeliev
    0.99
     Ratings
    0.96
    Rated
    0.95
     Rated
    0.91
     conflic
    0.91
     millenn
    0.89
    Activations Density 0.007%

    No Known Activations