© 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. 11-RES-JB
    11. 2460
    Prev
    Next
    INDEX
    Explanations

    medical conditions and treatments related to various illnesses

    oai_token-act-pair · gpt-3.5-turbo

    references to cancer and associated medical conditions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    éļ
    -0.81
    Guest
    -0.74
    soType
    -0.73
    calling
    -0.72
    TPS
    -0.72
     unification
    -0.71
     arrang
    -0.67
     Opening
    -0.66
    soDeliveryDate
    -0.65
    çķ
    -0.65
    POSITIVE LOGITS
     ingest
    1.24
     suffer
    1.16
     underwent
    1.12
     diagnosed
    1.11
     undergo
    1.09
     suffered
    1.03
     ingested
    1.03
     suffers
    1.03
     relapse
    1.02
     suffering
    1.02
    Activations Density 0.277%

    No Known Activations