© 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. 9-RES-JB
    11. 4653
    Prev
    Next
    INDEX
    Explanations

    mentions of geological terms related to tectonic activity

    oai_token-act-pair · gpt-3.5-turbo

    references to the word "asc" in various contexts

    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
    lda
    -0.75
    vironment
    -0.74
    zie
    -0.64
    DEN
    -0.64
    chy
    -0.63
    LOAD
    -0.62
    swer
    -0.61
    yip
    -0.61
    BALL
    -0.60
    zza
    -0.60
    POSITIVE LOGITS
    adia
    1.04
    ribed
    1.04
    ension
    0.97
    annon
    0.91
    adian
    0.90
    henko
    0.90
    ount
    0.88
    oly
    0.86
    otte
    0.85
    ape
    0.85
    Activations Density 0.045%

    No Known Activations