© 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. 7530
    Prev
    Next
    INDEX
    Explanations

    terms related to political movements and revolutionary ideas, specifically focused on liberation

    oai_token-act-pair · gpt-3.5-turbo

    terms related to the concept of liberation

    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
    ASON
    -0.75
     duplicate
    -0.75
     Cobb
    -0.70
    ype
    -0.67
    Series
    -0.67
    Spe
    -0.67
     Brewer
    -0.67
    Emb
    -0.67
    ardy
    -0.67
    Avg
    -0.64
    POSITIVE LOGITS
     liberation
    3.64
     Liberation
    3.03
     liberated
    2.52
     liberate
    2.33
     liberating
    2.30
     emancipation
    1.98
    liber
    1.94
     liber
    1.54
     freeing
    1.36
    freedom
    1.32
    Activations Density 0.030%

    No Known Activations