© 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. 8-RES-JB
    11. 6387
    Prev
    Next
    INDEX
    Explanations

    terms related to justice, fairness, and compassion

    oai_token-act-pair · gpt-3.5-turbo

    themes related to justice, fairness, and inclusivity in societal contexts

    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
    aunts
    -0.96
    hops
    -0.87
    planes
    -0.85
    events
    -0.82
    steps
    -0.82
    andals
    -0.80
    posts
    -0.80
    casts
    -0.80
    stones
    -0.79
    notes
    -0.78
    POSITIVE LOGITS
     environment
    1.17
     atmosphere
    1.09
     solution
    1.06
     relationship
    1.04
     outlook
    1.02
     outcome
    1.02
     approach
    1.00
     attitude
    0.97
     response
    0.96
     system
    0.94
    Activations Density 0.319%

    No Known Activations