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. 6-RES-JB
    6. 21402
    Prev
    Next
    INDEX
    Explanations

    verbs indicating movement or action in specific locations

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the preposition "to."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     thereof
    -0.81
    contained
    -0.69
    etheless
    -0.69
     transmitted
    -0.64
     compounded
    -0.64
     conveyed
    -0.62
     contrasted
    -0.62
    Moving
    -0.62
     Converted
    -0.61
    auga
    -0.61
    POSITIVE LOGITS
    pless
    0.80
     bed
    0.79
     buy
    0.74
     sleep
    0.72
     court
    0.72
    ying
    0.68
     hell
    0.67
     jail
    0.65
     play
    0.65
     shove
    0.65
    Activations Density 0.125%

    No Known Activations