© 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. 2-RES-JB
    11. 19526
    Prev
    Next
    INDEX
    Explanations

    medical conditions related to metabolism, particularly focusing on diabetes

    oai_token-act-pair · gpt-3.5-turbo

    mention of diabetes and related conditions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    semble
    -0.77
    agame
    -0.76
    Ń·
    -0.75
    bilt
    -0.73
    awatts
    -0.72
    steen
    -0.71
    achu
    -0.70
    vae
    -0.69
    rd
    -0.68
    AMS
    -0.66
    POSITIVE LOGITS
     mell
    1.33
     diabetes
    0.92
    abetes
    0.88
     Mell
    0.80
     glucose
    0.80
    esity
    0.80
     complications
    0.79
     Diabetes
    0.79
    roid
    0.77
     elbow
    0.77
    Activations Density 0.015%

    No Known Activations