© 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. 2-RES-JB
    11. 17344
    Prev
    Next
    INDEX
    Explanations

    words related to corporations or businesses, particularly with the suffix "inc" or "incidentally"

    oai_token-act-pair · gpt-3.5-turbo

    instances of the substring "inc" within words

    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
    ¥µ
    -1.10
    ĪĴ
    -0.93
    EStream
    -0.81
    EStreamFrame
    -0.68
     quo
    -0.68
    =-=-=-=-=-=-=-=-
    -0.67
     Balk
    -0.67
     Masters
    -0.67
    */(
    -0.64
    ħĭ
    -0.64
    POSITIVE LOGITS
    orporated
    1.59
    orpor
    1.29
    arcer
    1.27
    hester
    1.22
    endiary
    1.07
    identally
    1.04
    ision
    1.02
    redible
    1.01
    orrect
    0.97
    ounter
    0.96
    Activations Density 0.004%

    No Known Activations