© 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. 10-RES-JB
    11. 16676
    Prev
    Next
    INDEX
    Explanations

    phrases related to the Black Lives Matter movement

    oai_token-act-pair · gpt-3.5-turbo

    references to the Black Lives Matter movement

    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
    uin
    -0.73
    sonian
    -0.69
    Roberts
    -0.69
    Äĩ
    -0.69
    BIL
    -0.67
    pub
    -0.65
    ripp
    -0.65
    sweet
    -0.64
    ypes
    -0.63
    sort
    -0.63
    POSITIVE LOGITS
     Matter
    1.68
     Matters
    1.30
    matter
    1.17
     Lives
    0.88
     MAT
    0.87
     Liberation
    0.83
     Movement
    0.82
     matter
    0.82
    ives
    0.78
     Forever
    0.78
    Activations Density 0.025%

    No Known Activations