© 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. 4-RES-JB
    11. 22079
    Prev
    Next
    INDEX
    Explanations

    words related to the name "Berg", potentially as part of a name or related to a person with that name

    oai_token-act-pair · gpt-3.5-turbo

    references to individuals or groups with a surname or names resembling "Berg."

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

    No Comments

    Negative Logits
    İĭ
    -0.75
     Mub
    -0.71
     Fram
    -0.67
    ften
    -0.66
     virginity
    -0.63
     heart
    -0.61
    going
    -0.60
     Mi
    -0.59
    creen
    -0.58
     Promise
    -0.57
    POSITIVE LOGITS
    roup
    0.94
    ener
    0.93
    ling
    0.93
    onomic
    0.89
    ues
    0.88
    ERG
    0.87
    strom
    0.87
    ensen
    0.87
    reen
    0.86
    iazep
    0.86
    Activations Density 0.009%

    No Known Activations