© 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. 11-RES-JB
    11. 7809
    Prev
    Next
    INDEX
    Explanations

    scheduled events or appearances

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to scheduled appearances and potential legal outcomes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    è¦ļéĨĴ
    -0.75
     Checking
    -0.67
    76561
    -0.64
    ooks
    -0.63
    soType
    -0.62
     Catalog
    -0.62
    ahime
    -0.62
     taxing
    -0.62
     Editing
    -0.60
     adapters
    -0.60
    POSITIVE LOGITS
     plead
    1.46
     testify
    1.40
     face
    1.14
     undergo
    1.13
     receive
    1.09
     serve
    1.06
     remain
    1.06
     die
    1.06
     langu
    1.05
     forfeit
    1.04
    Activations Density 0.170%

    No Known Activations