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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 0-RES-JB
    11. 11291
    Prev
    Next
    INDEX
    Explanations

    phrases related to logical reasoning and conclusions

    oai_token-act-pair · gpt-3.5-turbo

    logical conclusions or statements that assert consequences or implications

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     barely
    -0.67
     skirm
    -0.65
     buzz
    -0.63
     trickle
    -0.63
     just
    -0.62
     kids
    -0.62
     nearly
    -0.61
     stalking
    -0.61
     pops
    -0.61
     pop
    -0.61
    POSITIVE LOGITS
     Therefore
    3.27
    Therefore
    3.01
     Consequently
    2.61
     Hence
    2.38
     Accordingly
    2.32
     Thus
    2.10
     therefore
    1.96
    Thus
    1.92
     Nevertheless
    1.92
     Furthermore
    1.85
    Activations Density 0.015%

    No Known Activations