© 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. 24046
    Prev
    Next
    INDEX
    Explanations

    phrases related to hate speech and hate crimes

    oai_token-act-pair · gpt-3.5-turbo

    terminology related to hate and hate crimes

    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
    aver
    -0.80
    UNCH
    -0.73
    Decre
    -0.72
    idges
    -0.72
    姫
    -0.71
     Examination
    -0.68
     Pione
    -0.68
    interstitial
    -0.68
    ufact
    -0.67
    ODE
    -0.67
    POSITIVE LOGITS
    fully
    1.10
    fulness
    1.09
     crimes
    0.96
    ful
    0.88
     vengeance
    0.85
     prejudice
    0.82
     speech
    0.79
    hound
    0.78
     crime
    0.77
     hate
    0.76
    Activations Density 0.030%

    No Known Activations