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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 7-RES-JB
    11. 15687
    Prev
    Next
    INDEX
    Explanations

    the word "Patch" with a strong preference for occurrences where it has a high activation value

    oai_token-act-pair · gpt-3.5-turbo

    terms related to software patches and updates

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     obser
    -0.75
    ¢
    -0.69
     Galile
    -0.66
    minist
    -0.66
     ministry
    -0.65
     trave
    -0.64
     contrad
    -0.64
    VERTISEMENT
    -0.64
     temptation
    -0.64
     FANT
    -0.63
    POSITIVE LOGITS
    work
    1.01
    ioned
    1.00
    ions
    0.92
    notes
    0.90
     Patch
    0.82
     patch
    0.82
    ion
    0.78
     patched
    0.78
    ION
    0.76
    hern
    0.76
    Activations Density 0.024%

    No Known Activations