© 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. 3-RES-JB
    11. 10775
    Prev
    Next
    INDEX
    Explanations

    phrases related to situations or consequences that occur without specific actions

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating the lack or absence of something

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    è¦ļéĨĴ
    -0.90
    ixel
    -0.77
    NRS
    -0.73
    des
    -0.73
    oola
    -0.72
    ounters
    -0.68
    ancial
    -0.68
    etimes
    -0.67
     murd
    -0.66
    dozen
    -0.65
    POSITIVE LOGITS
    lihood
    0.86
     Borders
    0.72
     knowing
    0.68
     mentioning
    0.67
    profit
    0.66
    lessly
    0.65
     exception
    0.64
     regard
    0.64
    withstanding
    0.64
     forgetting
    0.62
    Activations Density 0.022%

    No Known Activations