© 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. 4-RES-JB
    11. 20906
    Prev
    Next
    INDEX
    Explanations

    references to the term "Cent" which could be related to various topics such as economics, history, or specific events

    oai_token-act-pair · gpt-3.5-turbo

    references to the term "Cent" in various contexts

    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
    ãģį
    -0.83
    è¦ļéĨĴ
    -0.81
    isSpecialOrderable
    -0.80
    ãĥīãĥ©
    -0.74
    dfx
    -0.73
    INTER
    -0.72
    itably
    -0.71
    itable
    -0.69
    stakes
    -0.68
    ×ķ
    -0.68
    POSITIVE LOGITS
    rals
    1.01
    imet
    0.93
    ennial
    0.92
    uries
    0.89
    rones
    0.88
    enary
    0.87
    ritical
    0.86
    imeters
    0.86
    enario
    0.84
    rum
    0.84
    Activations Density 0.011%

    No Known Activations