© 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. 8-RES-JB
    11. 10822
    Prev
    Next
    INDEX
    Explanations

    phrases related to the concept of coming into a new state or condition

    oai_token-act-pair · gpt-3.5-turbo

    the phrase "come into" or similar constructs indicating transition or emergence

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    é¾
    -0.69
    killer
    -0.68
    _-
    -0.65
    dl
    -0.64
    cia
    -0.64
    lator
    -0.62
    gat
    -0.59
     TA
    -0.59
     await
    -0.58
    âĨij
    -0.58
    POSITIVE LOGITS
     fruition
    0.88
     adulthood
    0.83
    formed
    0.79
     existence
    0.79
     contact
    0.79
    jected
    0.78
    abeth
    0.78
     prominence
    0.76
    clusions
    0.75
     Sabha
    0.75
    Activations Density 0.042%

    No Known Activations