© 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. 10-RES-JB
    11. 24357
    Prev
    Next
    INDEX
    Explanations

    updates in a text or document

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "update" in various formats

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    athered
    -0.79
    stood
    -0.74
    aden
    -0.73
    anship
    -0.72
    ographies
    -0.70
    vernment
    -0.68
    wegian
    -0.67
    sbm
    -0.67
    anyon
    -0.67
    rouse
    -0.66
    POSITIVE LOGITS
    :
    1.08
     July
    1.07
     April
    1.06
     Feb
    1.04
     February
    1.04
     June
    1.04
     December
    1.02
     August
    1.01
     September
    0.99
     October
    0.99
    Activations Density 0.026%

    No Known Activations