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. 16334
    Prev
    Next
    INDEX
    Explanations

    actions or tasks that someone can start or complete

    oai_token-act-pair · gpt-3.5-turbo

    instances of conditional phrases or situations where actions depend on prior events

    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
     understatement
    -0.78
     Cosponsors
    -0.71
    ItemImage
    -0.64
     Nanto
    -0.62
     envy
    -0.62
     Surveillance
    -0.60
     Mong
    -0.60
     contrasts
    -0.60
     advoc
    -0.60
    é¾įå¥ij士
    -0.59
    POSITIVE LOGITS
    rosis
    0.90
     completes
    0.84
     mastered
    0.82
    hran
    0.79
    acqu
    0.79
    nir
    0.76
     finished
    0.76
    issan
    0.75
    leground
    0.75
     arrive
    0.75
    Activations Density 0.286%

    No Known Activations