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. 8-RES-JB
    6. 18423
    Prev
    Next
    INDEX
    Explanations

    sentences ending with a colon followed by a statement

    oai_token-act-pair · gpt-3.5-turbo

    statements or quotes made by individuals

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     trouble
    -0.69
     troubles
    -0.68
     giveaway
    -0.64
     delinquent
    -0.63
     overl
    -0.61
     controversy
    -0.60
     swaps
    -0.59
     shif
    -0.58
     stabilized
    -0.58
     popularity
    -0.57
    POSITIVE LOGITS
     "â̦
    1.27
     "...
    1.18
     "[
    1.15
     "'
    1.09
     '[
    1.08
     ""
    1.02
     "(
    0.98
     "@
    0.97
     ".
    0.96
     "#
    0.86
    Activations Density 0.092%

    No Known Activations