© 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. 10-RES-JB
    11. 8532
    Prev
    Next
    INDEX
    Explanations

    instances of drawing or depicting differences or outlines between various entities or concepts

    oai_token-act-pair · gpt-3.5-turbo

    phrases that involve drawing actions or comparisons

    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
    Ü
    -0.82
    hops
    -0.67
    ntil
    -0.66
    staking
    -0.65
    Boost
    -0.65
    TED
    -0.64
    ruciating
    -0.63
    pher
    -0.63
    speak
    -0.63
    Chance
    -0.60
    POSITIVE LOGITS
     conclusions
    1.31
     parallels
    1.08
     conclusion
    1.08
     curtains
    1.05
     ire
    1.05
     inference
    1.04
     attention
    0.90
     distinctions
    0.90
     line
    0.90
     lines
    0.87
    Activations Density 0.058%

    No Known Activations