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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 4-RES-JB
    11. 24028
    Prev
    Next
    INDEX
    Explanations

    mentions of causation or reason

    oai_token-act-pair · gpt-3.5-turbo

    references to the word "the" and phrases related to causation or reasoning

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

    No Comments

    Negative Logits
    ifies
    -0.83
    zon
    -0.73
    anon
    -0.70
    inates
    -0.69
    Fu
    -0.67
    Tel
    -0.67
    ESPN
    -0.67
    soever
    -0.67
    Joined
    -0.66
    agog
    -0.66
    POSITIVE LOGITS
     sheer
    0.99
     aforementioned
    0.95
     lack
    0.94
     impending
    0.90
     sudden
    0.90
     inherent
    0.89
     latter
    0.89
     circumstances
    0.87
     underlying
    0.85
     nature
    0.84
    Activations Density 0.447%

    No Known Activations