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

    Neuronpedia

    Jacobian LensNEW
    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. 15958
    Prev
    Next
    INDEX
    Explanations

    words related to patronage or supporting something

    oai_token-act-pair · gpt-3.5-turbo

    references to the concept of patrons or supporters

    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
    DX
    -0.84
    ARR
    -0.81
    AR
    -0.78
    MO
    -0.78
    REE
    -0.76
    eat
    -0.74
    LOD
    -0.74
    nesota
    -0.72
    RAM
    -0.72
    ARB
    -0.70
    POSITIVE LOGITS
     patron
    1.28
     patrons
    1.19
    isance
    0.88
     Patron
    0.88
    hetically
    0.87
    ordial
    0.79
     patronage
    0.78
     saint
    0.74
    umers
    0.73
     boosters
    0.71
    Activations Density 0.013%

    No Known Activations