© 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. 16054
    Prev
    Next
    INDEX
    Explanations

    second person pronouns followed by verbs

    oai_token-act-pair · gpt-3.5-turbo

    phrases that begin with "You"

    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
    ¿½
    -0.78
    adium
    -0.66
    ĸļ
    -0.66
    icy
    -0.64
    Politics
    -0.60
    polit
    -0.59
     Excellence
    -0.59
    interstitial
    -0.58
     Chap
    -0.58
     Scarborough
    -0.58
    POSITIVE LOGITS
    'll
    1.46
    're
    1.37
     guessed
    1.16
     can
    1.14
    've
    1.12
    'd
    0.99
     mileage
    0.98
     need
    0.98
     MUST
    0.96
     know
    0.95
    Activations Density 0.172%

    No Known Activations