© 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. 7-RES-JB
    11. 8845
    Prev
    Next
    INDEX
    Explanations

    phrases indicating high level of preparation or uniqueness

    oai_token-act-pair · gpt-3.5-turbo

    words that begin with the prefix "pre-"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ãĥīãĥ©ãĤ´ãĥ³
    -0.80
    loo
    -0.78
    è¦ļéĨĴ
    -0.74
    oice
    -0.72
     Weir
    -0.67
    IBLE
    -0.66
     GOODMAN
    -0.66
    BuyableInstoreAndOnline
    -0.65
    THING
    -0.63
    ãĤ¼ãĤ¦ãĤ¹
    -0.63
    POSITIVE LOGITS
    cision
    1.19
    requisite
    1.09
    pared
    1.09
    cise
    1.08
    requisites
    1.08
    ference
    1.05
    hens
    1.04
    hend
    1.03
    cious
    1.03
    fecture
    1.01
    Activations Density 0.024%

    No Known Activations