© 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 EvalsExportsinterp-engineNEWAPI 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. 15281
    Prev
    Next
    INDEX
    Explanations

    Russian text and possibly names

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of certain special characters or symbols, possibly indicating encoding issues or specific text formats

    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
    ierrez
    -0.79
    ebus
    -0.78
    cules
    -0.68
     tour
    -0.67
     Riley
    -0.66
    ptives
    -0.65
    cled
    -0.64
    Reviewer
    -0.64
    eredith
    -0.63
    aeda
    -0.63
    POSITIVE LOGITS
    ÑĮ
    1.22
    л
    1.21
    а
    1.15
    ĩ
    1.12
    е
    1.12
    и
    1.07
    Ñı
    1.06
    Ñ
    1.05
    Ĩ
    1.05
    оÐ
    1.03
    Activations Density 0.006%

    No Known Activations