© 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. 2-RES-JB
    11. 7032
    Prev
    Next
    INDEX
    Explanations

    words related to positivity and optimistic sentiments

    oai_token-act-pair · gpt-3.5-turbo

    expressions and sentiments related to positivity

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    RAW
    -0.85
    oths
    -0.78
    resp
    -0.76
    appings
    -0.74
    arij
    -0.74
    ANS
    -0.72
    adr
    -0.72
    pper
    -0.71
    ç«
    -0.70
    ourning
    -0.69
    POSITIVE LOGITS
     positive
    1.02
     reinforcement
    0.99
     affirmation
    0.91
     affirm
    0.90
     Positive
    0.87
    positive
    0.84
     feedback
    0.83
     Negative
    0.78
     buoy
    0.75
     outcome
    0.75
    Activations Density 0.016%

    No Known Activations