© 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. 18511
    Prev
    Next
    INDEX
    Explanations

    topics related to mental health and medical issues

    oai_token-act-pair · gpt-3.5-turbo

    negative connotations associated with health and social issues

    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
     Offer
    -0.73
     Centauri
    -0.72
     Pett
    -0.71
     Rowling
    -0.70
     Clyde
    -0.70
     Lauderdale
    -0.69
     Bil
    -0.69
     Cthulhu
    -0.68
     Fay
    -0.68
     McGregor
    -0.67
    POSITIVE LOGITS
    science
    1.17
    sounding
    1.14
    themed
    1.13
    related
    1.13
    technical
    1.10
    engineering
    1.08
    policy
    1.07
    induced
    1.06
    services
    1.06
    rights
    1.03
    Activations Density 0.117%

    No Known Activations