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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 1-RES-JB
    6. 7929
    Prev
    Next
    INDEX
    Explanations

    the word "concept" or related terms

    oai_token-act-pair · gpt-3.5-turbo

    key concepts or ideas related to a topic

    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
    tein
    -0.79
    cair
    -0.79
     hurd
    -0.73
    iland
    -0.73
     Hedge
    -0.72
     driveway
    -0.71
     answ
    -0.68
    ourt
    -0.66
    resa
    -0.66
    imore
    -0.64
    POSITIVE LOGITS
    Offline
    0.72
    zes
    0.71
     unfamiliar
    0.69
     familiar
    0.68
    weak
    0.67
    ______
    0.66
    ``
    0.65
    eware
    0.64
    voc
    0.63
    lua
    0.62
    Activations Density 0.000%

    No Known Activations