© 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. 3257
    Prev
    Next
    INDEX
    Explanations

    references to locations or institutions related to legal or international affairs

    oai_token-act-pair · gpt-3.5-turbo

    references to The Hague and associated institutions or entities

    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
    oor
    -0.74
    awar
    -0.71
    alach
    -0.68
    uel
    -0.65
    azeera
    -0.65
     mamm
    -0.63
    olis
    -0.61
    apter
    -0.60
     Scar
    -0.60
     sands
    -0.59
    POSITIVE LOGITS
     Crosby
    0.84
     Vital
    0.77
    Clar
    0.76
    animous
    0.75
    ifies
    0.74
    ifying
    0.70
    gement
    0.70
     Hague
    0.69
    sworth
    0.69
    sters
    0.67
    Activations Density 0.023%

    No Known Activations