© 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. 9-RES-JB
    11. 23341
    Prev
    Next
    INDEX
    Explanations

    verbs related to actions or processes

    oai_token-act-pair · gpt-3.5-turbo

    terms related to applications, institutions, and social concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     wont
    -0.74
     guessing
    -0.71
     characteristic
    -0.69
     sticking
    -0.66
     skipping
    -0.66
     loos
    -0.65
     checking
    -0.65
     wanting
    -0.65
     disappearing
    -0.65
     listening
    -0.65
    POSITIVE LOGITS
    ify
    1.43
    ize
    1.41
    ulate
    1.40
    rouse
    1.32
    itate
    1.30
    imize
    1.30
    activate
    1.29
    igrate
    1.27
    strate
    1.27
    ceive
    1.26
    Activations Density 0.447%

    No Known Activations