© 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. 10-RES-JB
    11. 12678
    Prev
    Next
    INDEX
    Explanations

    phrases that end with punctuations such as ")" or "?"

    oai_token-act-pair · gpt-3.5-turbo

    punctuation marks, particularly periods and question marks at the end of statements or questions

    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
    emaker
    -0.85
    lling
    -0.78
    legged
    -0.74
    ifying
    -0.72
    iliated
    -0.72
    apixel
    -0.72
    ilion
    -0.72
    urg
    -0.72
    icter
    -0.72
     advoc
    -0.70
    POSITIVE LOGITS
     Anyway
    1.64
    Anyway
    1.23
     Likewise
    1.22
     Regardless
    1.22
     Similarly
    1.18
     Meanwhile
    1.15
     Nevertheless
    1.15
     Nonetheless
    1.14
     Needless
    1.13
     Lastly
    1.13
    Activations Density 0.099%

    No Known Activations