© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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. 19730
    Prev
    Next
    INDEX
    Explanations

    occurrences of the term "COM" or "COMING" in the text

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the term "COM" in various contexts

    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
    ¶ħ
    -0.75
    ãĥĥãĥĪ
    -0.73
     Kubrick
    -0.70
    vae
    -0.69
    wagen
    -0.65
     Judaism
    -0.64
    Rand
    -0.64
    Ĭ±
    -0.63
    Ĥª
    -0.62
     Chern
    -0.61
    POSITIVE LOGITS
    BAT
    1.18
    MENTS
    1.12
    MENT
    1.06
    PLIC
    1.03
    PLA
    1.03
    COM
    0.98
    PL
    0.97
    FTWARE
    0.96
     COM
    0.96
    ply
    0.94
    Activations Density 0.008%

    No Known Activations