© 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. 4-RES-JB
    11. 3699
    Prev
    Next
    INDEX
    Explanations

    references to archaeology and archaeological terms

    oai_token-act-pair · gpt-3.5-turbo

    terms related to archaeology and archaeological studies

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

    No Comments

    Negative Logits
     unconditional
    -0.76
     Patient
    -0.72
    nir
    -0.71
     Toro
    -0.69
     Quadro
    -0.68
    otine
    -0.67
    Reloaded
    -0.67
    âķIJâķIJ
    -0.66
     MFT
    -0.65
     Senators
    -0.64
    POSITIVE LOGITS
     archae
    1.33
     Archae
    1.07
     archaeologists
    1.04
     excav
    1.04
     arte
    0.96
    ologist
    0.96
    ological
    0.93
    itect
    0.92
    ologists
    0.92
     archaeological
    0.91
    Activations Density 0.009%

    No Known Activations