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. 9653
    Prev
    Next
    INDEX
    Explanations

    words related to the desert or desertification

    oai_token-act-pair · gpt-3.5-turbo

    words that relate to the concept of 'despair' and its variations

    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
     Pavilion
    -0.74
     Pell
    -0.68
     offense
    -0.66
    mouth
    -0.65
     hypers
    -0.59
     Compton
    -0.58
     Fenrir
    -0.58
     Kimmel
    -0.56
     Dickinson
    -0.56
     Borders
    -0.56
    POSITIVE LOGITS
    dule
    0.90
    ãĥīãĥ©
    0.82
    utes
    0.79
    venge
    0.73
    ction
    0.72
    vation
    0.71
    igue
    0.71
    ues
    0.70
    oult
    0.70
    ember
    0.70
    Activations Density 0.054%

    No Known Activations