Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 8-RES-JB
    6. 5298
    Prev
    Next
    INDEX
    Explanations

    organizations or initiatives that involve taking action or making changes

    oai_token-act-pair · gpt-3.5-turbo

    action-oriented verbs related to advocacy and activism

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     constitu
    -0.79
     exha
    -0.68
    opausal
    -0.67
     discovery
    -0.65
     bottleneck
    -0.65
     tom
    -0.64
     discharge
    -0.63
     distortion
    -0.62
    ounter
    -0.62
     procedural
    -0.62
    POSITIVE LOGITS
    away
    1.24
    ings
    1.12
    aways
    1.05
    ners
    1.04
    ers
    0.99
     Yourself
    0.97
     Your
    0.96
     Away
    0.91
    ership
    0.89
    Maker
    0.88
    Activations Density 0.213%

    No Known Activations