© 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. 2-RES-JB
    11. 12572
    Prev
    Next
    INDEX
    Explanations

    the word "Stud" in various contexts

    oai_token-act-pair · gpt-3.5-turbo

    terms related to studying and education

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Centauri
    -0.74
    lessly
    -0.66
     exhaustion
    -0.66
     ending
    -0.66
     arsen
    -0.65
     tragically
    -0.63
    neum
    -0.63
     ageing
    -0.63
     Algeria
    -0.63
     expiration
    -0.63
    POSITIVE LOGITS
    stud
    1.04
    ents
    1.03
    Stud
    1.01
    ios
    0.89
    iano
    0.89
     Stud
    0.86
    enz
    0.84
    iors
    0.84
    sd
    0.81
    iple
    0.81
    Activations Density 0.015%

    No Known Activations