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. 18939
    Prev
    Next
    INDEX
    Explanations

    phrases indicating an action that happens before a specific event or outcome

    oai_token-act-pair · gpt-3.5-turbo

    phrases that indicate actions or events occurring prior to something else

    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
    hack
    -0.82
    Writer
    -0.69
    olog
    -0.67
    DC
    -0.67
    aez
    -0.66
    oret
    -0.66
    Die
    -0.65
    PROV
    -0.65
    amount
    -0.64
    NRS
    -0.64
    POSITIVE LOGITS
     sunset
    0.79
     committing
    0.74
     embark
    0.72
     sunrise
    0.71
     midnight
    0.70
     serving
    0.69
     realizing
    0.69
     Thumbnails
    0.67
     noon
    0.66
     supper
    0.66
    Activations Density 0.062%

    No Known Activations