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

    Neuronpedia

    APISteerSAE EvalsBlog/PodcastNEWSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlog/PodcastGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 5-RES-JB
    6. 338
    Prev
    Next
    INDEX
    Explanations

    medical conditions and disorders

    oai_token-act-pair · gpt-3.5-turbo

    terms related to various mental and behavioral disorders

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 5-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    5
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     snipp
    -0.69
    stanbul
    -0.66
    VO
    -0.65
     Pil
    -0.65
     Deer
    -0.63
    eworld
    -0.62
     Pione
    -0.62
    din
    -0.61
    riel
    -0.60
    é»Ĵ
    -0.60
    POSITIVE LOGITS
     disorders
    1.00
     diagnoses
    1.00
     Disorders
    0.95
     disorder
    0.92
     diagnosis
    0.88
    ipolar
    0.85
     worsen
    0.82
    iac
    0.82
     symptoms
    0.80
    mania
    0.80
    Activations Density 0.014%

    No Known Activations