Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlogSlackPrivacy & 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. 8-RES-JB
    6. 2879
    Prev
    Next
    INDEX
    Explanations

    names of people or characters

    oai_token-act-pair · gpt-3.5-turbo

    brands or specific titles related to products or media

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     metast
    -0.56
     stakes
    -0.53
     dashed
    -0.53
     rat
    -0.53
     embargo
    -0.52
     appointment
    -0.52
     crowd
    -0.52
     crowded
    -0.51
     industrial
    -0.50
     fine
    -0.50
    POSITIVE LOGITS
    opia
    0.72
    ukong
    0.71
    udo
    0.67
    atra
    0.66
    xxxx
    0.66
    DragonMagazine
    0.66
    Corp
    0.63
    arat
    0.62
    artz
    0.62
    Coin
    0.61
    Activations Density 0.646%

    No Known Activations