© 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. 9-RES-JB
    11. 16376
    Prev
    Next
    INDEX
    Explanations

    information related to health habits and recommendations

    oai_token-act-pair · gpt-3.5-turbo

    information related to health and wellness practices

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     jurisd
    -0.84
     alien
    -0.75
     elector
    -0.74
     Vill
    -0.71
     ambig
    -0.71
     Plaint
    -0.70
     [*]
    -0.70
    eller
    -0.70
    plom
    -0.69
     Franch
    -0.68
    POSITIVE LOGITS
     diet
    1.41
     calorie
    1.34
     fasting
    1.27
     caloric
    1.25
     diets
    1.17
     meals
    1.16
     habits
    1.15
     calories
    1.15
     abstinence
    1.15
     caffeine
    1.14
    Activations Density 0.822%

    No Known Activations