© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 2-RES-JB
    6. 12482
    Prev
    Next
    INDEX
    Explanations

    references to specific names or surnames

    oai_token-act-pair · gpt-3.5-turbo

    references to a specific political figure, Keith Ellison

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Smoking
    -0.71
    ework
    -0.71
    Ľ
    -0.67
    fulness
    -0.66
    VALUE
    -0.65
     Vlad
    -0.65
    PET
    -0.63
     [+
    -0.62
    worldly
    -0.61
    gary
    -0.61
    POSITIVE LOGITS
     Ellison
    1.10
    irez
    0.87
    eering
    0.76
    urations
    0.75
    entanyl
    0.69
    ando
    0.67
    igible
    0.67
    igent
    0.66
    psey
    0.65
    berg
    0.65
    Activations Density 0.007%

    No Known Activations