© 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. 24038
    Prev
    Next
    INDEX
    Explanations

    phrases that start with "While" followed by the use of active voice verbs

    oai_token-act-pair · gpt-3.5-turbo

    the phrase "while" to introduce contrasting situations or conditions

    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
    SPONSORED
    -0.77
    ISE
    -0.75
    tnc
    -0.73
    cause
    -0.72
    onica
    -0.68
    ixties
    -0.68
    INS
    -0.67
    icter
    -0.67
    die
    -0.67
    fleet
    -0.66
    POSITIVE LOGITS
     acknowledging
    1.24
     researching
    1.08
     conced
    0.96
     discussing
    0.93
     maintaining
    0.92
     admittedly
    0.90
     browsing
    0.90
     admitting
    0.89
     technically
    0.89
     there
    0.89
    Activations Density 0.057%

    No Known Activations