© 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. 4257
    Prev
    Next
    INDEX
    Explanations

    phrases indicating disagreement or criticism

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

    instances of the word "point" and its variations, indicating a focus on expressions of opinion or claims made in the text

    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
     seiz
    -0.66
    natureconservancy
    -0.65
    ccording
    -0.57
     ILCS
    -0.54
    cum
    -0.53
    ige
    -0.53
    ourt
    -0.53
    COL
    -0.52
    lap
    -0.51
    OOL
    -0.51
    POSITIVE LOGITS
     fingers
    1.09
     out
    0.98
     towards
    0.82
     toward
    0.80
     finger
    0.79
    edly
    0.75
    ly
    0.74
     to
    0.72
    lessly
    0.64
     us
    0.64
    Activations Density 0.049%

    No Known Activations