© 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. 11-RES-JB
    11. 20383
    Prev
    Next
    INDEX
    Explanations

    words related to acquiring or obtaining information or documents through some means

    oai_token-act-pair · gpt-3.5-turbo

    references to documents or records that have been obtained by various sources

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     rhy
    -0.63
     Nose
    -0.61
     tou
    -0.59
     tul
    -0.57
     cad
    -0.56
     nucleus
    -0.55
     rag
    -0.54
     rebirth
    -0.54
     reckoned
    -0.53
     destiny
    -0.53
    POSITIVE LOGITS
     exclusively
    1.15
     anonymously
    1.08
     pursuant
    0.91
     by
    0.89
    CLASSIFIED
    0.84
     via
    0.83
     THR
    0.83
    ault
    0.82
     firsthand
    0.81
     through
    0.81
    Activations Density 0.105%

    No Known Activations