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

    Neuronpedia

    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. 7-RES-JB
    11. 22846
    Prev
    Next
    INDEX
    Explanations

    words related to creation or establishment

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "created" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Mandatory
    -0.81
     Adin
    -0.74
    itte
    -0.70
    NetMessage
    -0.65
    Thom
    -0.61
     Krishna
    -0.59
    cgi
    -0.58
    pled
    -0.58
    externalActionCode
    -0.57
    PDATED
    -0.56
    POSITIVE LOGITS
    ãĥ¼ãĥĨãĤ£
    0.78
    rator
    0.73
    nces
    0.72
    emis
    0.71
    ulus
    0.71
    rious
    0.69
    stellar
    0.68
    arus
    0.68
    ulence
    0.68
     anew
    0.67
    Activations Density 0.049%

    No Known Activations