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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 2958
    Prev
    Next
    INDEX
    Explanations

    mentions of severe weather events, scientific developments, high-profile legal cases, and entertainment industry news

    oai_token-act-pair · gpt-3.5-turbo

    punctuation marks, particularly periods and exclamation points

    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
     allowance
    -0.74
     claimant
    -0.68
     alley
    -0.67
     advoc
    -0.67
     warr
    -0.66
     challeng
    -0.66
    inous
    -0.66
     perspect
    -0.66
    iev
    -0.66
     implication
    -0.65
    POSITIVE LOGITS
     Located
    1.13
     Luckily
    1.07
     Thankfully
    1.07
     Especially
    1.06
     Apparently
    1.04
     Yesterday
    1.04
     Sure
    1.03
     Literally
    1.02
     Seriously
    1.02
     Fortunately
    1.02
    Activations Density 0.441%

    No Known Activations