© 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. 8-RES-JB
    11. 18550
    Prev
    Next
    INDEX
    Explanations

    endings of sentences, especially those that are formatted like messages or tweets

    oai_token-act-pair · gpt-3.5-turbo

    sentences or clauses with a definitive ending or conclusion

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     gravy
    -0.86
     minim
    -0.82
     defe
    -0.77
     allowance
    -0.72
     transition
    -0.72
     transitions
    -0.72
     disadvantage
    -0.70
     warr
    -0.70
     disadvantages
    -0.70
     unob
    -0.69
    POSITIVE LOGITS
     Specifically
    1.33
     According
    1.27
     Whereas
    1.25
     Called
    1.23
     Located
    1.18
     Instead
    1.15
     Firstly
    1.15
     Apparently
    1.15
     Beginning
    1.13
     Featuring
    1.13
    Activations Density 0.469%

    No Known Activations