© 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. 10-RES-JB
    11. 10492
    Prev
    Next
    INDEX
    Explanations

    sentences starting with "Here's" presenting information or explanations

    oai_token-act-pair · gpt-3.5-turbo

    repeated or emphasized symbols or characters

    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
     balk
    -0.75
     disadvant
    -0.73
     mathemat
    -0.72
     bankrupt
    -0.68
     feas
    -0.68
     triv
    -0.67
     snowball
    -0.66
     unaff
    -0.66
     comr
    -0.65
     inefficient
    -0.64
    POSITIVE LOGITS
    ï¸ı
    1.13
    shall
    0.94
    here
    0.90
    ould
    0.88
    there
    0.88
    t
    0.85
     denotes
    0.85
    ind
    0.85
    reve
    0.84
    above
    0.83
    Activations Density 0.130%

    No Known Activations