© 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. 7-RES-JB
    11. 13448
    Prev
    Next
    INDEX
    Explanations

    phrases involving the act of speaking or expressing thoughts/opinions

    oai_token-act-pair · gpt-3.5-turbo

    instances of speech or quotations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    xtap
    -0.81
    ritional
    -0.76
    ãĥ´
    -0.74
    folios
    -0.70
    equipped
    -0.70
    pleting
    -0.69
    phrine
    -0.69
    agascar
    -0.66
    mental
    -0.66
     Flavoring
    -0.66
    POSITIVE LOGITS
     goodbye
    1.65
     hello
    1.25
     aloud
    1.09
     farewell
    1.04
     bye
    1.00
     Goodbye
    0.95
     hi
    0.90
     loudly
    0.88
     sorry
    0.81
    ieu
    0.81
    Activations Density 0.169%

    No Known Activations