© 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. 7-RES-JB
    11. 11239
    Prev
    Next
    INDEX
    Explanations

    words related to specific groups or entities that the subject interacts with

    oai_token-act-pair · gpt-3.5-turbo

    group affiliations and roles within various social, political, and international contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     seiz
    -0.68
     Heist
    -0.67
    leck
    -0.64
    ocaust
    -0.63
    SHIP
    -0.63
    ]}
    -0.63
    ]=
    -0.63
     Purg
    -0.61
    Pg
    -0.61
    %]
    -0.60
    POSITIVE LOGITS
     counterparts
    0.83
     colleagues
    0.73
    friends
    0.71
     representatives
    0.71
     coworkers
    0.71
    omever
    0.70
    «ĺ
    0.66
     buddies
    0.66
     classmates
    0.65
     partners
    0.65
    Activations Density 0.613%

    No Known Activations