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

    Neuronpedia

    Jacobian LensNEW
    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. 10-RES-JB
    11. 6242
    Prev
    Next
    INDEX
    Explanations

    web links

    oai_token-act-pair · gpt-3.5-turbo

    the presence of punctuation marks, particularly periods, indicating the end of sentences

    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
     tremend
    -0.89
    »Ĵ
    -0.87
    ŃĶ
    -0.84
     teasp
    -0.77
    ãĥĺ
    -0.77
     fucked
    -0.76
    ĪĴ
    -0.74
    illet
    -0.73
    ually
    -0.73
     horrend
    -0.73
    POSITIVE LOGITS
     Others
    1.62
     Critics
    1.46
     They
    1.29
     Some
    1.26
     Experts
    1.25
     Supporters
    1.23
     Advoc
    1.22
     Officials
    1.19
     Their
    1.19
     Indeed
    1.19
    Activations Density 0.377%

    No Known Activations