© 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. 10260
    Prev
    Next
    INDEX
    Explanations

    verbs related to caring or concern

    oai_token-act-pair · gpt-3.5-turbo

    expressions of concern or disregard for various issues and values

    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
    UES
    -0.73
    GV
    -0.68
     perjury
    -0.60
    ======
    -0.59
    anas
    -0.59
    oute
    -0.59
    CHA
    -0.58
    ãĥĪ
    -0.58
     Transcript
    -0.56
    antha
    -0.56
    POSITIVE LOGITS
    lessly
    1.15
     passionately
    1.11
    der
    0.99
    taker
    0.98
    lessness
    0.95
     deeply
    0.81
    fully
    0.81
    bear
    0.80
     cared
    0.80
    ened
    0.79
    Activations Density 0.024%

    No Known Activations