© 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 EvalsExportsinterp-engineNEWAPI 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. 6-RES-JB
    11. 9377
    Prev
    Next
    INDEX
    Explanations

    phrases indicating setting out to do something

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating intentions or goals related to setting out on a journey or undertaking a project

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     elderly
    -0.65
     reopened
    -0.62
     closed
    -0.58
     wrap
    -0.57
     passers
    -0.57
     endings
    -0.57
     impacted
    -0.56
     lif
    -0.56
     bowl
    -0.55
    lif
    -0.55
    POSITIVE LOGITS
    sonian
    0.91
    ngth
    0.78
    é¾įåĸļ士
    0.73
    ãģ¦
    0.73
    mberg
    0.73
    llor
    0.72
    ////////////////////////////////
    0.71
    ÑĢ
    0.71
    AAF
    0.69
    ////////
    0.69
    Activations Density 0.030%

    No Known Activations