© 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. 2733
    Prev
    Next
    INDEX
    Explanations

    phrases related to receiving or subscribing to news alerts and reports

    oai_token-act-pair · gpt-3.5-turbo

    keywords related to breaking news and alerts

    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
    ovo
    -0.59
    ivas
    -0.56
     Prosecut
    -0.55
     displacement
    -0.55
     monop
    -0.54
    bors
    -0.54
     Leaf
    -0.53
     barg
    -0.53
     quir
    -0.53
    oos
    -0.52
    POSITIVE LOGITS
    ickets
    0.78
    interstitial
    0.70
    ricanes
    0.65
    catentry
    0.61
    uracy
    0.60
    weather
    0.60
    dayName
    0.59
    DERR
    0.58
    omaly
    0.58
    ļéĨĴ
    0.56
    Activations Density 0.024%

    No Known Activations