© 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. 12501
    Prev
    Next
    INDEX
    Explanations

    mentions or discussions related to scholars

    oai_token-act-pair · gpt-3.5-turbo

    mentions of scholars and scholarly activities

    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
     Labrador
    -0.80
     Valkyrie
    -0.64
     999
    -0.62
     territ
    -0.62
     Guam
    -0.61
     Territories
    -0.60
     December
    -0.58
     vicinity
    -0.58
     landfall
    -0.57
     Ventura
    -0.57
    POSITIVE LOGITS
    sonian
    1.19
     scholars
    1.10
     scholar
    1.04
    hip
    0.98
    olars
    0.96
     Scholars
    0.96
    ¿½
    0.95
    abilia
    0.86
     interpre
    0.82
     historians
    0.76
    Activations Density 0.014%

    No Known Activations