© 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. 1-RES-JB
    11. 22558
    Prev
    Next
    INDEX
    Explanations

    phrases or sentence endings that indicate a strong opinion or conclusion

    oai_token-act-pair · gpt-3.5-turbo

    end punctuation marks that signify the conclusion of statements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     metic
    -0.88
     purse
    -0.85
    ling
    -0.78
     encount
    -0.77
    thal
    -0.76
     earthqu
    -0.76
     corrid
    -0.76
    ibur
    -0.76
     challeng
    -0.75
     skelet
    -0.74
    POSITIVE LOGITS
    Downloadha
    1.16
     Flavoring
    1.07
     Unless
    1.07
    Reviewer
    1.06
     Especially
    1.01
     Therefore
    1.01
     Otherwise
    1.00
     Ideally
    0.99
     Depending
    0.98
     However
    0.98
    Activations Density 1.582%

    No Known Activations