© 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. 6664
    Prev
    Next
    INDEX
    Explanations

    names or terms related to the word "Gir"

    oai_token-act-pair · gpt-3.5-turbo

    mentions of specific organizations or entities

    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
    ãĥĩãĤ£
    -0.72
     Contra
    -0.69
     Samoa
    -0.66
    ãĥ¼ãĥĨ
    -0.65
     solvent
    -0.60
     Sevent
    -0.59
    ħĭ
    -0.59
    opsy
    -0.59
    ittee
    -0.59
     Archdemon
    -0.58
    POSITIVE LOGITS
    affe
    1.19
    aldi
    0.94
     Gir
    0.92
    oux
    0.92
    rier
    0.85
     Pengu
    0.84
    vana
    0.83
    acha
    0.81
    kees
    0.80
    aval
    0.80
    Activations Density 0.008%

    No Known Activations