© 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. 12579
    Prev
    Next
    INDEX
    Explanations

    verbs that describe influence, action or consequence

    oai_token-act-pair · gpt-3.5-turbo

    verbs that indicate the presentation of information and analysis

    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
     Ascension
    -0.65
     introduction
    -0.62
    اÙĦ
    -0.61
    tone
    -0.59
     Antar
    -0.58
    Bey
    -0.57
    away
    -0.57
    zo
    -0.56
    bearing
    -0.54
     Unle
    -0.54
    POSITIVE LOGITS
    ettings
    1.06
    paces
    1.03
    hift
    0.99
    omething
    0.96
    ometimes
    0.96
    hirt
    0.92
    pace
    0.88
    creen
    0.87
    ynthesis
    0.85
    ilver
    0.85
    Activations Density 0.320%

    No Known Activations