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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 11-RES-JB
    11. 24471
    Prev
    Next
    INDEX
    Explanations

    words related to various topics such as skiing, electricity, democracy, colors, cryptocurrencies, transportation, therapeutic interventions, and botanical substances

    oai_token-act-pair · gpt-3.5-turbo

    terms related to various significant topics including sports, technology, morality, and life challenges

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     subsequ
    -0.58
     fruitful
    -0.58
     recognised
    -0.57
    pired
    -0.56
    ailable
    -0.55
    akening
    -0.55
     requisite
    -0.52
     realise
    -0.52
    eret
    -0.52
    este
    -0.51
    POSITIVE LOGITS
    âĢ
    1.46
     âĢ
    1.07
    .*
    1.05
    *.
    1.03
    .</
    1.03
    _.
    1.02
    .�
    1.01
    âĢł
    0.96
    .#
    0.95
     âĶ
    0.91
    Activations Density 0.516%

    No Known Activations