© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 3-RES-JB
    11. 625
    Prev
    Next
    INDEX
    Explanations

    references to solid or liquid drops or deposits

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the word "dro" and its variations in different contexts

    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
     Clause
    -0.77
    é¾įå¥ij士
    -0.76
     reconciliation
    -0.76
     Canary
    -0.75
     Trident
    -0.75
    ãĥĨãĤ£
    -0.74
    ãĥ¯ãĥ³
    -0.71
     Ou
    -0.71
     Reverend
    -0.66
    Reviewer
    -0.66
    POSITIVE LOGITS
    plets
    1.26
    plet
    1.20
    ppers
    1.11
    pper
    1.00
    cks
    0.94
     dro
    0.93
    ves
    0.91
    ble
    0.89
    ppings
    0.87
    pless
    0.87
    Activations Density 0.011%

    No Known Activations