© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 19217
    Prev
    Next
    INDEX
    Explanations

    mentions of specific locations or organizations, particularly "Lands," "Marks," "Graves," and "Isles."

    oai_token-act-pair · gpt-3.5-turbo

    mentions of specific geographical terms or entities

    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
    TABLE
    -0.72
     Yus
    -0.71
     captcha
    -0.67
     induct
    -0.66
    UFC
    -0.64
     induction
    -0.61
     proven
    -0.61
    âĨ
    -0.60
     ted
    -0.59
    capt
    -0.59
    POSITIVE LOGITS
     Lands
    2.44
     Siem
    0.74
     Nord
    0.71
    glers
    0.70
     Isles
    0.70
    keyes
    0.69
    owship
    0.69
    earchers
    0.69
    budget
    0.68
     Macy
    0.67
    Activations Density 0.004%

    No Known Activations