© 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. 13582
    Prev
    Next
    INDEX
    Explanations

    pronouns and verbs indicating action or decision-making

    oai_token-act-pair · gpt-3.5-turbo

    the presence and actions of specific individuals in conditional contexts

    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
    GROUND
    -0.71
    Magikarp
    -0.67
    PORT
    -0.67
    interstitial
    -0.66
     ILCS
    -0.62
    HCR
    -0.58
    Est
    -0.57
    MpServer
    -0.56
    enhagen
    -0.56
    kef
    -0.56
    POSITIVE LOGITS
     survives
    1.12
     weren
    1.11
     ever
    1.09
     succeeds
    1.08
     fails
    1.07
     hadn
    1.01
     stays
    0.97
     persists
    0.97
     chooses
    0.96
     continues
    0.95
    Activations Density 0.121%

    No Known Activations