© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 18744
    Prev
    Next
    INDEX
    Explanations

    words related to negative consequences or issues

    oai_token-act-pair · gpt-3.5-turbo

    words and phrases that indicate negative emotional or stressful situations

    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
    aucas
    -0.59
    estone
    -0.58
     carrot
    -0.58
    ©¶æ
    -0.57
     ANN
    -0.56
    ynski
    -0.54
    cknow
    -0.54
     playbook
    -0.54
     toe
    -0.54
     violet
    -0.54
    POSITIVE LOGITS
     amongst
    0.86
     among
    0.85
     akin
    0.78
     havoc
    0.74
    .<
    0.70
     downstream
    0.69
     elsewhere
    0.69
     wherever
    0.69
    among
    0.68
     throughout
    0.66
    Activations Density 0.327%

    No Known Activations