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. 7-RES-JB
    6. 10485
    Prev
    Next
    INDEX
    Explanations

    phrases or sentences describing situations or characteristics in a negative or critical light

    oai_token-act-pair · gpt-3.5-turbo

    references to painting or depicting situations, conditions, or characteristics through figurative language

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    staking
    -0.68
    lease
    -0.68
    amba
    -0.67
    orship
    -0.67
    utenberg
    -0.66
    atches
    -0.66
    iencies
    -0.63
    arthed
    -0.63
    otrop
    -0.63
     reproduce
    -0.61
    POSITIVE LOGITS
     bleak
    0.81
     differently
    0.78
    TextColor
    0.75
     gloom
    0.74
     picture
    0.72
     vividly
    0.69
     Draper
    0.69
     gloomy
    0.68
     dystopian
    0.67
     portrait
    0.67
    Activations Density 0.288%

    No Known Activations