© 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. 10-RES-JB
    11. 20665
    Prev
    Next
    INDEX
    Explanations

    mentions of hate crimes and hate speech

    oai_token-act-pair · gpt-3.5-turbo

    mentions of hate crimes and related terminology

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    UNCH
    -0.76
    aver
    -0.71
    amina
    -0.70
    enture
    -0.70
    clinton
    -0.69
     reluct
    -0.69
    ITNESS
    -0.68
     Prospect
    -0.68
    BuyableInstoreAndOnline
    -0.68
    atel
    -0.67
    POSITIVE LOGITS
    fulness
    1.13
     crimes
    1.13
     speech
    1.05
    fully
    1.02
    ful
    0.97
     crime
    0.95
    speech
    0.91
     Crimes
    0.88
     Speech
    0.88
     mobs
    0.88
    Activations Density 0.044%

    No Known Activations