© 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. 0-RES-JB
    11. 11353
    Prev
    Next
    INDEX
    Explanations

    terms related to legislation and unity within a political context

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of "BR," likely indicating a specific entity or tag related to business reporting

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Turing
    -0.70
     scales
    -0.65
     Voy
    -0.63
     contra
    -0.62
     Ele
    -0.62
     Eugene
    -0.62
     prosecut
    -0.60
     relat
    -0.59
     habit
    -0.59
     Tut
    -0.59
    POSITIVE LOGITS
    BR
    4.21
     BR
    1.84
    br
    1.73
    FR
    1.60
    BE
    1.54
    Br
    1.50
    KR
    1.47
    BU
    1.46
    BL
    1.42
    BRE
    1.40
    Activations Density 0.014%

    No Known Activations