Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 20101
    Prev
    Next
    INDEX
    Explanations

    actions involving the movement or placement of objects

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of actions and items related to building or creating

    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
    imity
    -0.84
    >]
    -0.75
    nces
    -0.66
     opposing
    -0.65
     rivalry
    -0.65
     terrorism
    -0.65
     Recent
    -0.64
     historically
    -0.63
    entious
    -0.63
    chance
    -0.63
    POSITIVE LOGITS
    ertodd
    0.95
     THEN
    0.90
    then
    0.88
     Then
    0.87
    Then
    0.86
     vo
    0.86
     prest
    0.85
    went
    0.79
     then
    0.78
     rinse
    0.76
    Activations Density 0.917%

    No Known Activations