© 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. 13700
    Prev
    Next
    INDEX
    Explanations

    various forms of the word "another" and related words, such as "second" and "other."

    oai_token-act-pair · gpt-3.5-turbo

    references to alternative options or viewpoints

    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
    Crew
    -0.79
    ULTS
    -0.78
     Shots
    -0.78
     Bleach
    -0.78
    pees
    -0.77
    Staff
    -0.75
     Pwr
    -0.75
    enery
    -0.74
    aturdays
    -0.74
    osures
    -0.74
    POSITIVE LOGITS
     fallacy
    1.36
     theorem
    1.29
     implication
    1.28
     methodological
    1.28
     normative
    1.25
     empirical
    1.23
     epist
    1.23
     presupp
    1.22
     criterion
    1.22
     fundamental
    1.19
    Activations Density 0.282%

    No Known Activations