© 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. 6-RES-JB
    11. 11815
    Prev
    Next
    INDEX
    Explanations

    names or words related to political figures or entities

    oai_token-act-pair · gpt-3.5-turbo

    references to individuals or entities characterized by the term "erg."

    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
    İĭ
    -0.85
     Mub
    -0.74
    going
    -0.68
     Fram
    -0.67
    ©¶æ¥µ
    -0.63
    ften
    -0.62
    ĺħ
    -0.62
    fty
    -0.62
    LOAD
    -0.62
    creen
    -0.61
    POSITIVE LOGITS
    roup
    0.96
    ensen
    0.92
    raham
    0.90
    ling
    0.89
    reen
    0.89
    onomic
    0.87
    raphic
    0.87
    ues
    0.85
    roups
    0.84
    lings
    0.83
    Activations Density 0.016%

    No Known Activations