© 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. 6-RES-JB
    11. 7383
    Prev
    Next
    INDEX
    Explanations

    concerns related to social justice and activism

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to social roles and stereotypes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Ports
    -0.70
     Pebble
    -0.68
    ventory
    -0.67
    raft
    -0.67
    Wind
    -0.66
    Temperature
    -0.65
    orsche
    -0.65
    ebus
    -0.65
     Agility
    -0.64
    romeda
    -0.64
    POSITIVE LOGITS
     rapists
    1.02
     dehuman
    1.01
     stigmat
    1.00
     rapist
    0.98
     feminists
    0.98
     misogyn
    0.96
     rape
    0.96
     patriarchal
    0.94
     shaming
    0.93
     feminist
    0.92
    Activations Density 1.596%

    No Known Activations