© 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. 3-RES-JB
    11. 23990
    Prev
    Next
    INDEX
    Explanations

    phrases related to enrollment, especially in an educational context

    oai_token-act-pair · gpt-3.5-turbo

    terms related to enrollment and registration processes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    yip
    -0.88
    ongyang
    -0.74
    osate
    -0.73
    apest
    -0.71
    uesday
    -0.66
    levard
    -0.66
     incon
    -0.65
    appropriate
    -0.64
    hops
    -0.63
     organ
    -0.62
    POSITIVE LOGITS
    enment
    1.12
    ciating
    1.11
    yll
    0.73
    achment
    0.73
    oyer
    0.72
    EMENT
    0.72
    ctr
    0.72
     Lauder
    0.70
    ãĤ¨ãĥ«
    0.70
    agement
    0.70
    Activations Density 0.119%

    No Known Activations