Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlogSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 2-RES-JB
    6. 16904
    Prev
    Next
    INDEX
    Explanations

    medical conditions or related symptoms, specifically focused on fever.

    oai_token-act-pair · gpt-3.5-turbo

    references to fever and related symptoms or 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
    */(
    -0.88
    ĻĤ
    -0.74
    twitter
    -0.65
    AAF
    -0.65
    raped
    -0.64
    ribute
    -0.64
    VICE
    -0.64
    model
    -0.64
     Judges
    -0.64
    OTT
    -0.64
    POSITIVE LOGITS
     fever
    1.12
    ishly
    0.97
     Fever
    0.84
    few
    0.84
    emia
    0.78
    idious
    0.76
    ãĥ¼ãĥĨ
    0.73
     nood
    0.73
    ãĥ¼ãĥĨãĤ£
    0.71
    oster
    0.71
    Activations Density 0.009%

    No Known Activations