© 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. 12-RES-JB
    11. 4549
    Prev
    Next
    INDEX
    Explanations

    first-person singular pronouns used in a self-reflective or explanatory context

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot

    first-person singular pronouns

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 12-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.hook_resid_post
    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_post
    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
     passers
    -0.57
     occurrences
    -0.56
     offsets
    -0.55
     impunity
    -0.54
     indications
    -0.54
     sparks
    -0.53
     srfAttach
    -0.53
     manifests
    -0.50
     prompts
    -0.50
     indicators
    -0.50
    POSITIVE LOGITS
    stanbul
    1.10
    nex
    1.06
    van
    0.97
    rene
    0.95
    vana
    0.95
    gor
    0.93
    zzy
    0.92
    rina
    0.91
    vy
    0.89
    EEE
    0.89
    Activations Density 0.161%

    No Known Activations