Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 1-RES-JB
    6. 23957
    Prev
    Next
    INDEX
    Explanations

    references to historians in text

    oai_token-act-pair · gpt-3.5-turbo

    references to historians and scholarly analysis

    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
    ply
    -0.80
    chy
    -0.80
    arter
    -0.76
    pose
    -0.72
     Lumpur
    -0.72
     unconditional
    -0.72
    ramid
    -0.70
    cheon
    -0.69
    eat
    -0.68
    legate
    -0.68
    POSITIVE LOGITS
     historian
    1.24
     historians
    1.13
     nostalg
    1.04
     buffs
    0.92
     archaeologists
    0.86
    abilia
    0.86
    orically
    0.85
     histor
    0.84
    orians
    0.83
     scholar
    0.81
    Activations Density 0.011%

    No Known Activations