© 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. 2-RES-JB
    11. 17763
    Prev
    Next
    INDEX
    Explanations

    words or phrases related to null values or situations

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "null."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Downloadha
    -0.72
    hens
    -0.71
     millenn
    -0.71
    ilitating
    -0.68
    UGE
    -0.67
    è¦ļéĨĴ
    -0.67
    BOOK
    -0.66
    ETF
    -0.66
    ODY
    -0.66
    Reviewer
    -0.65
    POSITIVE LOGITS
    ifies
    0.96
    ptr
    0.95
    ifying
    0.94
    ified
    0.89
    ities
    0.88
    ity
    0.84
    ify
    0.84
    igible
    0.78
    ification
    0.77
    ius
    0.77
    Activations Density 0.012%

    No Known Activations