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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 3-RES-JB
    11. 15059
    Prev
    Next
    INDEX
    Explanations

    terms related to feminism

    oai_token-act-pair · gpt-3.5-turbo

    terms related to feminism and its various interpretations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     guiActiveUnfocused
    -0.85
    Assembly
    -0.76
     Solitaire
    -0.67
    ------------------------------------------------
    -0.64
     Redemption
    -0.64
     haunt
    -0.64
    enance
    -0.63
     Cunning
    -0.63
    hog
    -0.63
     orally
    -0.62
    POSITIVE LOGITS
    initions
    1.14
    inity
    1.12
    ine
    1.11
    inem
    1.08
    emin
    1.05
    inant
    1.04
    istries
    1.04
    azi
    1.03
    iners
    1.01
    inite
    0.99
    Activations Density 0.011%

    No Known Activations