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

    Neuronpedia

    Jacobian LensNEW
    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. 11-RES-JB
    11. 7494
    Prev
    Next
    INDEX
    Explanations

    phrases related to positions, organizations, or events

    oai_token-act-pair · gpt-3.5-turbo

    phrases concerning governance or organizational structures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     scanner
    -0.71
     scoop
    -0.70
    ãĤ©
    -0.64
    anchez
    -0.63
     reign
    -0.63
     crow
    -0.63
     overrun
    -0.62
     habitat
    -0.61
     pairing
    -0.59
     fleet
    -0.59
    POSITIVE LOGITS
     Churches
    1.11
     Experts
    1.06
     Ministers
    1.01
     Parties
    0.85
     Representatives
    0.84
     Associ
    0.84
    soType
    0.83
     Learned
    0.82
     Directors
    0.81
     Authors
    0.80
    Activations Density 0.071%

    No Known Activations