© 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. 20233
    Prev
    Next
    INDEX
    Explanations

    words related to specific topics or areas, particularly those related to science, health, accidents, relationships, and policies

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to science or health topics

    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
    IVER
    -0.77
    AUT
    -0.74
     Barnett
    -0.73
    ample
    -0.70
     Meridian
    -0.69
    ãĤ©
    -0.69
     SOLD
    -0.68
    \\\\\\\\
    -0.65
    ifter
    -0.65
     Sinai
    -0.63
    POSITIVE LOGITS
    related
    1.09
     proble
    0.98
    tenance
    0.95
     related
    0.91
     unrelated
    0.86
     newsp
    0.85
     challeng
    0.82
    ativity
    0.82
     conflic
    0.82
    merce
    0.80
    Activations Density 0.009%

    No Known Activations