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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlogSlackPrivacy & 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. 18880
    Prev
    Next
    INDEX
    Explanations

    articles published in scientific journals like "Nature" and "Science."

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the journal "Nature" and related scientific publications

    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
    haul
    -0.81
     piping
    -0.71
     perjury
    -0.71
     maid
    -0.68
     awoken
    -0.63
     leveled
    -0.63
     attendant
    -0.62
     boycot
    -0.62
     militar
    -0.62
     ceilings
    -0.62
    POSITIVE LOGITS
     Genetics
    1.06
     Communications
    1.05
     Psychiatry
    1.05
     Publishing
    0.98
     Materials
    0.97
    Chem
    0.97
     Biology
    0.96
     Methods
    0.96
     Letters
    0.95
     Communication
    0.95
    Activations Density 0.047%

    No Known Activations