© 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. 3-RES-JB
    11. 3893
    Prev
    Next
    INDEX
    Explanations

    random characters and phrases that do not form any coherent pattern or meaningful text

    oai_token-act-pair · gpt-3.5-turbo

    specific characters or symbols, particularly degrees and special characters

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    antha
    -0.79
    ormal
    -0.79
    istics
    -0.77
    ilater
    -0.74
    auder
    -0.73
    ajo
    -0.72
     strikers
    -0.72
    alog
    -0.72
    ority
    -0.71
    stri
    -0.70
    POSITIVE LOGITS
    ·
    1.37
    °
    1.22
    ¸
    1.20
    ¾
    1.12
    µ
    1.11
    ½
    1.06
    ı
    1.05
    ¶
    1.04
    Ĺ
    1.03
    ¼
    1.03
    Activations Density 0.008%

    No Known Activations