© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 1-RES-JB
    11. 13164
    Prev
    Next
    INDEX
    Explanations

    phrases related to specific companies or organizations, particularly those with acronyms like GN and GNU

    oai_token-act-pair · gpt-3.5-turbo

    references to the General Nuclear Energy (GN) and related organizations

    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
    nee
    -0.72
    tes
    -0.72
     Ingram
    -0.69
    bell
    -0.69
     school
    -0.67
     Wolver
    -0.66
     Painter
    -0.63
     Highlands
    -0.63
    quer
    -0.61
     Mour
    -0.60
    POSITIVE LOGITS
    GN
    1.18
    emonic
    1.02
    SS
    0.88
    esta
    0.88
    OME
    0.82
    ativity
    0.81
    ostic
    0.81
    ivable
    0.81
    iciary
    0.81
    uggets
    0.81
    Activations Density 0.009%

    No Known Activations