© 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. 3452
    Prev
    Next
    INDEX
    Explanations

    sentence transitions or conjunctions indicating continuation or contrast

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to probability and potential consequences

    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
     everywhere
    -0.55
     racket
    -0.55
     apocalypse
    -0.53
     fever
    -0.52
     junk
    -0.51
    iasco
    -0.51
    ????????
    -0.50
     forever
    -0.50
    chwitz
    -0.49
     yesterday
    -0.49
    POSITIVE LOGITS
     outwe
    0.78
    etheless
    0.72
    higher
    0.70
     disadvantages
    0.68
    better
    0.67
    oother
    0.65
     softer
    0.64
     preferable
    0.64
     smoother
    0.63
    advant
    0.63
    Activations Density 1.003%

    No Known Activations