© 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. 12032
    Prev
    Next
    INDEX
    Explanations

    instances of people or things being freed or released from a constraint or restriction

    oai_token-act-pair · gpt-3.5-turbo

    mentions of individuals or entities being released from captivity or constraints

    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
     MMR
    -0.92
    aval
    -0.77
    umbers
    -0.67
     Spokane
    -0.66
     NHL
    -0.66
    atton
    -0.66
    ography
    -0.65
     smear
    -0.65
    boards
    -0.62
    agger
    -0.62
    POSITIVE LOGITS
     freed
    3.78
     liberated
    2.48
     freeing
    2.37
     emanc
    1.80
     liberate
    1.64
     Freed
    1.62
     liberating
    1.62
     reclaimed
    1.54
     enslaved
    1.52
     emancipation
    1.37
    Activations Density 0.017%

    No Known Activations