© 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. 21776
    Prev
    Next
    INDEX
    Explanations

    positive or negative sentiments in the text

    oai_token-act-pair · gpt-3.5-turbo

    words conveying positive and negative sentiments

    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
    ocene
    -0.84
     flaws
    -0.74
    iens
    -0.73
     loopholes
    -0.72
    Offline
    -0.68
     methods
    -0.67
    resources
    -0.65
     mistakes
    -0.65
    ador
    -0.65
    Attempts
    -0.64
    POSITIVE LOGITS
     correlated
    0.85
     charged
    0.85
     oriented
    0.83
     impacting
    0.83
     disposed
    0.82
     inclined
    0.80
     positively
    0.79
     positioned
    0.77
     attracted
    0.77
     interacted
    0.76
    Activations Density 0.008%

    No Known Activations