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. 10-RES-JB
    6. 20249
    Prev
    Next
    INDEX
    Explanations

    sensitive information related to classified documents and criminal activities

    oai_token-act-pair · gpt-3.5-turbo

    references to the word "the" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ledge
    -0.78
    olicy
    -0.76
    hett
    -0.75
    merce
    -0.75
     teasp
    -0.74
    ageddon
    -0.74
    lopp
    -0.74
    govtrack
    -0.74
     arises
    -0.72
    æĹ
    -0.72
    POSITIVE LOGITS
     same
    1.12
     defendant
    0.95
     wrong
    0.92
     infamous
    0.89
     gunman
    0.88
     rapper
    0.88
     USS
    0.87
     assailant
    0.87
     teenager
    0.86
     alias
    0.85
    Activations Density 0.392%

    No Known Activations