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

    Neuronpedia

    Jacobian LensNEW
    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. 21204
    Prev
    Next
    INDEX
    Explanations

    organizations or groups being led by someone

    oai_token-act-pair · gpt-3.5-turbo

    phrases that indicate leadership or groups being led by individuals

    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
     Scotia
    -0.76
    iddler
    -0.65
     Allaah
    -0.61
     sunset
    -0.61
     Addiction
    -0.59
    arest
    -0.58
    entric
    -0.58
     age
    -0.56
     Remastered
    -0.55
    mopolitan
    -0.55
    POSITIVE LOGITS
    gers
    1.24
    ges
    1.12
    gling
    1.05
    ging
    1.04
    better
    1.02
    ger
    1.01
    ged
    0.91
    ership
    0.86
    gest
    0.85
    semb
    0.80
    Activations Density 0.035%

    No Known Activations