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. 6797
    Prev
    Next
    INDEX
    Explanations

    words related to violent or forceful actions, such as 'splattering' or 'ashing'

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "splash" or its variations

    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
    Reviewer
    -0.74
    manship
    -0.73
     negligence
    -0.71
    geist
    -0.70
    culosis
    -0.69
    Downloadha
    -0.68
    jriwal
    -0.67
    hammad
    -0.66
    eers
    -0.64
    ³³³³³³³³³³³³³³³³
    -0.64
    POSITIVE LOGITS
    attered
    1.05
    atters
    0.94
    inters
    0.93
    atform
    0.92
    atter
    0.91
    atoon
    0.89
    itting
    0.88
    ashing
    0.87
    atical
    0.87
    attering
    0.86
    Activations Density 0.006%

    No Known Activations