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. 10-RES-JB
    6. 1961
    Prev
    Next
    INDEX
    Explanations

    words related to publishing and releasing information

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    rail
    -0.87
    usa
    -0.81
    cone
    -0.75
    ft
    -0.70
    ombat
    -0.70
    ï¸
    -0.68
    restling
    -0.67
    usp
    -0.67
    uay
    -0.66
    avery
    -0.66
    POSITIVE LOGITS
     information
    1.13
     anything
    1.03
    ulate
    1.01
     transcripts
    0.99
     confidential
    0.96
     truthful
    0.96
     excerpts
    0.95
     details
    0.94
     inaccurate
    0.94
     updates
    0.94
    Activations Density 0.185%

    No Known Activations