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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 1-RES-JB
    11. 16891
    Prev
    Next
    INDEX
    Explanations

    the phrase "Black Lives Matter" and related mentions

    oai_token-act-pair · gpt-3.5-turbo

    references to the phrase "Black Lives Matter."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     relax
    -0.71
    VIS
    -0.71
     VIS
    -0.68
     decl
    -0.67
    ripp
    -0.67
    Hyper
    -0.66
    insert
    -0.65
    ieu
    -0.64
    EStreamFrame
    -0.63
    NetMessage
    -0.63
    POSITIVE LOGITS
     Lives
    1.27
    ©¶æ
    0.98
     Matter
    0.97
     Rebell
    0.94
     Forever
    0.93
    lihood
    0.88
     Matters
    0.82
    matter
    0.77
     Frie
    0.77
    uti
    0.75
    Activations Density 0.005%

    No Known Activations