© 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. 21837
    Prev
    Next
    INDEX
    Explanations

    phrases related to significant impact or harm

    oai_token-act-pair · gpt-3.5-turbo

    words that describe severe negative impacts or effects

    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
    cius
    -0.90
    annis
    -0.79
    ploma
    -0.78
    ublic
    -0.71
    rity
    -0.71
    endment
    -0.70
    ioch
    -0.69
    swick
    -0.68
    porter
    -0.68
    guyen
    -0.68
    POSITIVE LOGITS
    ly
    1.04
     devast
    0.96
     blow
    0.95
     havoc
    0.89
     shocks
    0.85
     blows
    0.85
    ãĥ¼ãĥĨ
    0.80
     devastation
    0.80
     earthqu
    0.77
     impacts
    0.76
    Activations Density 0.013%

    No Known Activations