© 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. 2-RES-JB
    11. 441
    Prev
    Next
    INDEX
    Explanations

    the word "liberty"

    oai_token-act-pair · gpt-4-turbo

    references to the concept of "liberty."

    oai_token-act-pair · gpt-3.5-turbo

    references to the concept of liberty

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    HEAD
    -0.75
    gaard
    -0.73
    PAR
    -0.71
    Production
    -0.67
    PM
    -0.66
    ergy
    -0.65
    AMS
    -0.65
    Electric
    -0.59
    Bi
    -0.59
    outed
    -0.59
    POSITIVE LOGITS
     liberties
    1.05
     liberty
    1.02
     Liberties
    0.97
    fulness
    0.92
    tarian
    0.86
    freedom
    0.85
    tarians
    0.84
     freedoms
    0.82
    acies
    0.79
    ously
    0.78
    Activations Density 0.010%

    No Known Activations