© 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. 7-RES-JB
    11. 21179
    Prev
    Next
    INDEX
    Explanations

    sentences expressing positive opinions about individuals, particularly in a professional context

    oai_token-act-pair · gpt-3.5-turbo

    expressions of admiration and appreciation for individuals

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     unspecified
    -0.62
    specified
    -0.60
    PDF
    -0.59
     congressional
    -0.54
    illance
    -0.53
     unprotected
    -0.53
    pdf
    -0.53
    orum
    -0.52
     unlawful
    -0.52
     unconstitutional
    -0.52
    POSITIVE LOGITS
     mentors
    0.76
     compliment
    0.75
     compliments
    0.73
     humility
    0.73
     empath
    0.66
    Favorite
    0.66
     inspirational
    0.65
     motivate
    0.65
     ment
    0.65
    laughs
    0.65
    Activations Density 1.023%

    No Known Activations