© 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. 0-RES-JB
    11. 22792
    Prev
    Next
    INDEX
    Explanations

    types of materials

    oai_token-act-pair · gpt-3.5-turbo

    references to different types or forms of material

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ï¸ı
    -0.77
    hey
    -0.72
    orah
    -0.72
    igate
    -0.70
     Startup
    -0.66
    borgh
    -0.66
    nie
    -0.64
     congr
    -0.62
    iesta
    -0.62
    slow
    -0.61
    POSITIVE LOGITS
     material
    3.83
    material
    2.93
     Material
    2.60
     materials
    2.51
    Material
    2.17
     Materials
    1.78
    Materials
    1.47
     materially
    1.41
     substance
    1.33
     mater
    1.31
    Activations Density 0.021%

    No Known Activations