© 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 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. 10-RES-JB
    11. 16662
    Prev
    Next
    INDEX
    Explanations

    references to specific numerical figures or verses

    oai_token-act-pair · gpt-3.5-turbo

    punctuation marks, particularly periods that indicate the end of a statement

    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
     quir
    -0.85
     targeted
    -0.82
     partnered
    -0.81
     cloning
    -0.81
     booking
    -0.80
     snowball
    -0.80
     interns
    -0.79
     coordinated
    -0.78
     volunte
    -0.78
     trending
    -0.76
    POSITIVE LOGITS
     Thus
    1.43
    CHAPTER
    1.41
     Suppose
    1.41
     Accordingly
    1.41
     Hence
    1.40
     Therefore
    1.31
    Thus
    1.29
     Notwithstanding
    1.26
     Consequently
    1.24
     Cf
    1.22
    Activations Density 0.211%

    No Known Activations