© 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. 1-RES-JB
    11. 3186
    Prev
    Next
    INDEX
    Explanations

    words related to medical treatment or assistance

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the word "treated" in various contexts relating to actions or conditions involving individuals or groups

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    aer
    -0.78
    audi
    -0.63
     Rae
    -0.61
    azi
    -0.60
    sign
    -0.60
    export
    -0.58
    sky
    -0.57
    crypt
    -0.56
    bi
    -0.56
    hang
    -0.56
    POSITIVE LOGITS
     treated
    0.97
    ttes
    0.92
     Pwr
    0.86
     aback
    0.86
    illance
    0.85
    ricular
    0.83
     Treatment
    0.83
    ouble
    0.82
    reatment
    0.82
    treated
    0.80
    Activations Density 0.012%

    No Known Activations