© 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. 2-RES-JB
    11. 19510
    Prev
    Next
    INDEX
    Explanations

    text related to legal matters or copyright notices

    oai_token-act-pair · gpt-3.5-turbo

    references to "material" in various contexts, emphasizing its significance and legal considerations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ort
    -0.66
    etts
    -0.65
    alty
    -0.65
    ovation
    -0.63
     Parables
    -0.62
    ARP
    -0.61
    aird
    -0.61
    CHR
    -0.61
     Hatch
    -0.60
    erd
    -0.59
    POSITIVE LOGITS
     material
    0.87
    utonium
    0.82
     Material
    0.80
    izes
    0.76
     materials
    0.75
    edly
    0.74
    ulty
    0.74
    estine
    0.73
    worm
    0.73
    ized
    0.73
    Activations Density 0.011%

    No Known Activations