© 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. 9-RES-JB
    11. 15491
    Prev
    Next
    INDEX
    Explanations

    sentences or short phrases that end with punctuation marks

    oai_token-act-pair · gpt-3.5-turbo

    punctuation marks, particularly periods and exclamation points

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     commissioned
    -0.82
     planned
    -0.81
     millenn
    -0.81
     intended
    -0.80
     predec
    -0.80
     concess
    -0.79
     authorized
    -0.79
     emanc
    -0.78
     differential
    -0.77
     designated
    -0.76
    POSITIVE LOGITS
     Anyway
    1.58
    Anyway
    1.53
     Especially
    1.40
     [/
    1.25
     Honestly
    1.23
     Secondly
    1.21
     Sorry
    1.20
     ;)
    1.19
     Besides
    1.16
     Seriously
    1.15
    Activations Density 0.433%

    No Known Activations