© 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 EvalsExportsinterp-engineNEWAPI 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. 11-RES-JB
    11. 2857
    Prev
    Next
    INDEX
    Explanations

    sentences with the word "two" or phrases indicating dual aspects/topics/parts

    oai_token-act-pair · gpt-3.5-turbo

    sentences that mention quantities or lists of items

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     wonders
    -0.66
     billions
    -0.58
    enance
    -0.55
    oro
    -0.55
    rup
    -0.54
    letes
    -0.54
    earch
    -0.54
    unning
    -0.53
     millions
    -0.53
    uble
    -0.52
    POSITIVE LOGITS
     Firstly
    1.32
     Both
    1.25
     One
    1.19
    one
    1.19
    first
    1.09
    Firstly
    1.08
     one
    1.08
    Both
    1.07
    One
    1.01
     Neither
    1.00
    Activations Density 0.285%

    No Known Activations