© 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. 3996
    Prev
    Next
    INDEX
    Explanations

    phrases related to mass measurement and distribution

    oai_token-act-pair · gpt-3.5-turbo

    references to mass in various contexts

    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
    sbm
    -0.79
    BOOK
    -0.68
    nos
    -0.66
    --------------------------------------------------------
    -0.64
     Ital
    -0.63
    ©¶æ
    -0.62
    ãĤ¼
    -0.62
    BILITIES
    -0.61
    chy
    -0.61
     Oriental
    -0.61
    POSITIVE LOGITS
    achusetts
    1.26
    achus
    0.85
     quantities
    0.80
    ographically
    0.73
    -(
    0.71
    irth
    0.70
     incarceration
    0.69
    izable
    0.69
    imil
    0.69
     drift
    0.69
    Activations Density 0.009%

    No Known Activations