© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 4-RES-JB
    6. 7591
    Prev
    Next
    INDEX
    Explanations

    numbers indicating the quantity or frequency of specific events or conditions

    oai_token-act-pair · gpt-3.5-turbo

    mentions of various cases, particularly related to health or medical incidents

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

    No Comments

    Negative Logits
    roe
    -0.72
     livest
    -0.70
    asus
    -0.70
     streng
    -0.68
    FORMATION
    -0.67
    owered
    -0.67
     mathemat
    -0.64
    eele
    -0.64
    apo
    -0.63
    liction
    -0.63
    POSITIVE LOGITS
    cases
    0.98
     cases
    0.92
     involving
    0.90
    cale
    0.77
    20439
    0.74
    vati
    0.72
    manship
    0.72
    afety
    0.69
    uations
    0.69
     instances
    0.68
    Activations Density 0.025%

    No Known Activations