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. 9531
    Prev
    Next
    INDEX
    Explanations

    social media and email sharing options

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to emailing and sharing content

    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
    fig
    -0.71
    natureconservancy
    -0.61
    krit
    -0.61
    ngth
    -0.60
    omaly
    -0.59
    quished
    -0.59
    terness
    -0.58
     upside
    -0.58
     toppled
    -0.57
    hement
    -0.57
    POSITIVE LOGITS
    PsyNetMessage
    0.85
     Morse
    0.81
     Whats
    0.77
    âĢ¢âĢ¢
    0.70
    instein
    0.67
     Cancel
    0.67
     Nieto
    0.66
    Fax
    0.64
    istration
    0.64
    letters
    0.63
    Activations Density 0.098%

    No Known Activations