© 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. 6347
    Prev
    Next
    INDEX
    Explanations

    positive or negative sentiment and the impact of actions

    oai_token-act-pair · gpt-3.5-turbo

    terms related to positive sentiment and ratings

    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
    plain
    -0.94
    Hide
    -0.84
    uble
    -0.81
    hner
    -0.76
    ptin
    -0.76
    cffff
    -0.74
    lay
    -0.73
    racuse
    -0.73
    Invalid
    -0.73
    igs
    -0.73
    POSITIVE LOGITS
     reinforcement
    1.36
     feedback
    1.16
     gearing
    1.07
     vib
    1.05
     outlook
    1.00
     outcomes
    0.99
     portrayal
    0.98
     attitude
    0.96
     publicity
    0.96
     impact
    0.95
    Activations Density 0.067%

    No Known Activations