© 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. 2828
    Prev
    Next
    INDEX
    Explanations

    studies or research that are referenced or mentioned

    oai_token-act-pair · gpt-3.5-turbo

    references to research studies and data reports

    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
     goodbye
    -0.77
     Actions
    -0.68
     Nib
    -0.65
    Cooldown
    -0.64
     loyalty
    -0.64
    Dialogue
    -0.63
     dear
    -0.63
     hugs
    -0.63
     Petty
    -0.61
    natureconservancy
    -0.61
    POSITIVE LOGITS
    uggest
    1.52
     showed
    1.35
     concluded
    1.33
     examined
    1.26
     analyzed
    1.21
     revealed
    1.19
     uncovered
    1.17
     indicated
    1.15
     suggested
    1.14
     analysed
    1.14
    Activations Density 0.273%

    No Known Activations