© 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. 22445
    Prev
    Next
    INDEX
    Explanations

    references to particular acronyms, especially those related to official titles or positions

    oai_token-act-pair · gpt-3.5-turbo

    references to political figures or titles

    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
    furt
    -0.79
    lihood
    -0.79
    ãĥ¼ãĥĨ
    -0.78
    ãĤ¡
    -0.74
    glers
    -0.74
     sidx
    -0.72
    ibility
    -0.71
    via
    -0.71
    âĸĪâĸĪ
    -0.70
    rets
    -0.69
    POSITIVE LOGITS
    ipop
    0.87
    ODE
    0.83
    CP
    0.83
     CM
    0.82
    trop
    0.81
    CM
    0.78
    OS
    0.76
    OUNT
    0.76
    apper
    0.74
    oly
    0.74
    Activations Density 0.004%

    No Known Activations