© 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. 3-RES-JB
    11. 582
    Prev
    Next
    INDEX
    Explanations

    references to legal or authoritative figures, particularly those with titles like "editor" or "solicitor"

    oai_token-act-pair · gpt-3.5-turbo

    words or phrases related to legal or professional roles

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ©
    -0.75
    ©¶æ
    -0.70
    sett
    -0.66
    ¥ŀ
    -0.65
    param
    -0.64
    GoldMagikarp
    -0.64
    sterdam
    -0.62
    CAST
    -0.61
    ·
    -0.61
     understanding
    -0.60
    POSITIVE LOGITS
    ious
    1.21
    itor
    1.20
    ial
    1.04
    itors
    1.03
    berus
    1.03
    ium
    1.00
    iously
    0.99
    IAL
    0.92
    ionage
    0.88
    ially
    0.84
    Activations Density 0.013%

    No Known Activations