© 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. 8-RES-JB
    11. 4162
    Prev
    Next
    INDEX
    Explanations

    positive sentiments or mentions

    oai_token-act-pair · gpt-3.5-turbo

    references to positive outcomes or evaluations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    appings
    -0.90
    puter
    -0.87
    oths
    -0.86
    ngth
    -0.84
    ptin
    -0.81
    atum
    -0.81
    ometimes
    -0.78
    alian
    -0.78
    ĸļ
    -0.76
    hower
    -0.76
    POSITIVE LOGITS
     reinforcement
    1.13
     feedback
    1.01
     outcome
    0.97
     outlook
    0.96
     vib
    0.96
     attitude
    0.91
     appraisal
    0.90
     affirm
    0.86
     outcomes
    0.84
     affirmation
    0.84
    Activations Density 0.043%

    No Known Activations