© 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. 9-RES-JB
    11. 10061
    Prev
    Next
    INDEX
    Explanations

    phrases related to deprivation or loss of something

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to deprivation or loss of rights and resources

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    agate
    -0.95
    ilst
    -0.91
    avis
    -0.72
    wcsstore
    -0.72
    strip
    -0.72
     Cosponsors
    -0.71
    antis
    -0.71
    opus
    -0.69
    Chem
    -0.69
    ammers
    -0.69
    POSITIVE LOGITS
     freedoms
    1.34
     liberty
    1.27
     valuable
    1.21
     privileges
    1.15
     freedom
    1.14
     liberties
    1.12
     dignity
    1.11
     rights
    1.11
     autonomy
    1.10
     sovereignty
    1.05
    Activations Density 0.195%

    No Known Activations