© 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. 4-RES-JB
    11. 9497
    Prev
    Next
    INDEX
    Explanations

    information about personal experiences and reflections

    oai_token-act-pair · gpt-3.5-turbo

    the presence of punctuation, particularly periods

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

    No Comments

    Negative Logits
     criminal
    -0.75
    anche
    -0.72
     unequ
    -0.71
    oshenko
    -0.71
    ue
    -0.71
     opponent
    -0.70
     tack
    -0.69
     camoufl
    -0.68
     submerged
    -0.68
     opposing
    -0.68
    POSITIVE LOGITS
     Thankfully
    1.26
     Luckily
    1.20
     Hopefully
    1.14
     Unfortunately
    1.14
     Fortunately
    1.11
     Sadly
    1.08
     However
    1.07
     Especially
    1.04
     But
    1.03
     :)
    1.01
    Activations Density 0.782%

    No Known Activations