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. 3-RES-JB
    6. 13716
    Prev
    Next
    INDEX
    Explanations

    instances of words related to sharp or gripping actions

    oai_token-act-pair · gpt-3.5-turbo

    words related to claws and paws

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Nare
    -0.83
    acht
    -0.72
    ItemImage
    -0.70
    Interstitial
    -0.70
    Else
    -0.69
    Liber
    -0.67
    Aust
    -0.66
    Rah
    -0.65
    Republic
    -0.65
     Demand
    -0.65
    POSITIVE LOGITS
     claws
    1.22
     claw
    1.07
    bones
    0.98
     Claw
    0.93
    cheon
    0.89
     paws
    0.84
    geoning
    0.82
     nails
    0.80
     hooks
    0.79
    aws
    0.79
    Activations Density 0.012%

    No Known Activations