© 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. 491
    Prev
    Next
    INDEX
    Explanations

    the root "ver" as part of larger words, indicating truth or verification

    oai_token-act-pair · gpt-4-turbo

    general terms related to verification and confirmation

    oai_token-act-pair · gpt-3.5-turbo

    words related to verification or confirmation

    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
    hyde
    -0.93
    NetMessage
    -0.83
    »Ĵ
    -0.77
    OPLE
    -0.72
    ered
    -0.72
    hetti
    -0.71
    ĩ
    -0.69
    emi
    -0.69
    OWER
    -0.66
    oresc
    -0.66
    POSITIVE LOGITS
    bal
    1.04
     ver
    1.02
    ifiable
    0.98
    itable
    0.95
    ific
    0.88
    ulent
    0.83
    dict
    0.83
    ifies
    0.81
    ver
    0.79
    anda
    0.79
    Activations Density 0.008%

    No Known Activations