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. 9-RES-JB
    6. 16984
    Prev
    Next
    INDEX
    Explanations

    phrases related to taking action or making decisions

    oai_token-act-pair · gpt-3.5-turbo

    comparative phrases and similes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    resy
    -0.74
    emi
    -0.67
    ennes
    -0.67
    aced
    -0.66
    ims
    -0.66
    ells
    -0.65
    iership
    -0.65
    oir
    -0.64
    rovers
    -0.63
    WI
    -0.63
    POSITIVE LOGITS
    lihood
    1.37
    lier
    0.84
     removing
    0.80
     those
    0.80
    liest
    0.79
     skipping
    0.79
     deleting
    0.79
     altering
    0.76
     dropping
    0.75
     stealing
    0.73
    Activations Density 0.086%

    No Known Activations