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

    Neuronpedia

    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. 3-RES-JB
    11. 1787
    Prev
    Next
    INDEX
    Explanations

    words related to negative impacts or harms, particularly with a strong negative effect

    oai_token-act-pair · gpt-3.5-turbo

    references to negative impacts or setbacks

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    iosity
    -0.79
     guiIcon
    -0.72
    cius
    -0.67
    Definition
    -0.67
    rian
    -0.66
    orkshire
    -0.66
    HCR
    -0.65
    afort
    -0.65
    heid
    -0.65
    pora
    -0.64
    POSITIVE LOGITS
    blow
    0.90
    outs
    0.88
     blow
    0.88
     blows
    0.84
     retard
    0.82
    pipe
    0.81
    hole
    0.81
    out
    0.81
    bang
    0.81
     Blow
    0.79
    Activations Density 0.012%

    No Known Activations