© 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. 4-RES-JB
    11. 1779
    Prev
    Next
    INDEX
    Explanations

    terms related to small liquid droplets

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "dro" and its variations, indicating a focus on specific lexical items related to a particular context or concept

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

    No Comments

    Negative Logits
     Clause
    -0.76
     Trident
    -0.75
    ãĥĨãĤ£
    -0.74
     reconciliation
    -0.73
    ãĥ¯ãĥ³
    -0.72
     specificity
    -0.71
    ãĥ¤
    -0.70
     Ou
    -0.69
    é¾įå¥ij士
    -0.68
    è£ħ
    -0.67
    POSITIVE LOGITS
    plets
    1.27
    plet
    1.17
    ppers
    1.09
    pper
    0.99
    ves
    0.98
    cks
    0.93
    pless
    0.89
    uling
    0.89
    ppings
    0.87
     dro
    0.87
    Activations Density 0.007%

    No Known Activations