© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 3-RES-JB
    11. 6534
    Prev
    Next
    INDEX
    Explanations

    phrases related to warnings or alerts

    oai_token-act-pair · gpt-3.5-turbo

    assertive statements about opinions or beliefs

    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
    Joined
    -0.47
    bryce
    -0.44
     Ce
    -0.42
    rones
    -0.40
    ife
    -0.40
     Built
    -0.39
     Bund
    -0.39
    white
    -0.38
    wives
    -0.37
    gang
    -0.37
    POSITIVE LOGITS
     disclaim
    0.56
     anecd
    0.55
     surprises
    0.55
     caveats
    0.54
     hindsight
    0.53
     caveat
    0.51
     explanations
    0.50
    etheless
    0.50
     luck
    0.48
     caution
    0.47
    Activations Density 4.890%

    No Known Activations