© 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. 14932
    Prev
    Next
    INDEX
    Explanations

    terms related to serving a purpose or function

    oai_token-act-pair · gpt-3.5-turbo

    phrases that convey the function or purpose of something

    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
    ascus
    -0.77
    orne
    -0.68
    clone
    -0.67
    orph
    -0.66
    razil
    -0.65
    vu
    -0.64
    ilateral
    -0.62
     uncontroll
    -0.61
    pled
    -0.61
    phrine
    -0.61
    POSITIVE LOGITS
    HTTP
    0.87
     SERV
    0.78
    ctuary
    0.76
     Serving
    0.75
     meals
    0.75
     kitchens
    0.73
    maid
    0.73
    Channel
    0.73
    ãĥĺ
    0.71
     served
    0.71
    Activations Density 0.022%

    No Known Activations