© 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. 1-RES-JB
    11. 3222
    Prev
    Next
    INDEX
    Explanations

    instances of the word "filing" in various contexts

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "filing."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    osate
    -0.81
    oly
    -0.79
    ophe
    -0.73
    appy
    -0.68
    cott
    -0.66
    atomic
    -0.65
     unres
    -0.65
     Wilkinson
    -0.64
     nutrit
    -0.64
    revolution
    -0.63
    POSITIVE LOGITS
     filing
    1.23
     filings
    1.22
     deadlines
    1.02
     filed
    0.97
     Deadline
    0.97
     descriptor
    0.90
     deadline
    0.89
    DAQ
    0.81
     cabinets
    0.78
     documents
    0.74
    Activations Density 0.004%

    No Known Activations