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. 8-RES-JB
    6. 21599
    Prev
    Next
    INDEX
    Explanations

    phrases related to technology and innovation

    oai_token-act-pair · gpt-3.5-turbo

    content related to process and change

    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
    hement
    -0.99
    feed
    -0.64
    ighth
    -0.64
    lected
    -0.63
    abouts
    -0.61
    aday
    -0.60
    finger
    -0.60
    bryce
    -0.59
    going
    -0.59
    baugh
    -0.58
    POSITIVE LOGITS
    ³³³³³³³³³³³³³³³³
    0.88
    ccording
    0.83
    ³³³³³³³³
    0.81
    ³³³
    0.76
    ³³³³
    0.74
     Similar
    0.68
     Rape
    0.67
     Throughout
    0.67
     Debate
    0.64
     Regardless
    0.63
    Activations Density 0.147%

    No Known Activations