© 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. 21708
    Prev
    Next
    INDEX
    Explanations

    names or terms related to specific locations

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the abbreviation "vi" and its variations

    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
    */(
    -0.78
     Cosponsors
    -0.75
    rooms
    -0.72
    spin
    -0.67
    ¥µ
    -0.65
    lain
    -0.64
    ĭ
    -0.63
     Observer
    -0.63
     Heard
    -0.62
    landish
    -0.62
    POSITIVE LOGITS
    vi
    1.07
    ñ
    1.02
    Äį
    0.95
    uld
    0.94
    Äĩ
    0.90
    irus
    0.88
    ault
    0.88
    agra
    0.87
    ña
    0.86
    itri
    0.85
    Activations Density 0.007%

    No Known Activations