© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 4-RES-JB
    11. 4885
    Prev
    Next
    INDEX
    Explanations

    phrases indicating consideration or inclusion of various factors

    oai_token-act-pair · gpt-3.5-turbo

    the phrase "take into account."

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

    No Comments

    Negative Logits
    dot
    -0.65
    late
    -0.63
    edly
    -0.62
    owl
    -0.61
    atile
    -0.61
    zai
    -0.60
    die
    -0.60
    aroo
    -0.59
    don
    -0.59
    end
    -0.59
    POSITIVE LOGITS
    kef
    0.76
     adulthood
    0.76
    displayText
    0.71
    vernment
    0.71
    pload
    0.70
    ital
    0.67
    clusion
    0.67
    æ©
    0.65
     Banking
    0.65
     Sabb
    0.64
    Activations Density 0.030%

    No Known Activations