© 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. 12006
    Prev
    Next
    INDEX
    Explanations

    phrases related to ambition or aspiration

    oai_token-act-pair · gpt-3.5-turbo

    references to conspiracy theories

    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
    usc
    -0.77
     heap
    -0.73
     dispatch
    -0.69
     dismiss
    -0.66
     reservation
    -0.65
     Chandler
    -0.65
     locality
    -0.65
     points
    -0.63
     precincts
    -0.63
     fielding
    -0.62
    POSITIVE LOGITS
    pir
    4.25
    piracy
    1.80
    pire
    1.75
    piring
    1.68
    piration
    1.64
    Pir
    1.39
    pired
    1.35
     Pirate
    1.19
    pires
    1.18
     Pirates
    0.94
    Activations Density 0.002%

    No Known Activations