© 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. 2-RES-JB
    11. 10469
    Prev
    Next
    INDEX
    Explanations

    phrases indicating a need for reconciliation or contrast between different elements

    oai_token-act-pair · gpt-3.5-turbo

    terms related to comparison and balancing opposing elements

    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
     Chimera
    -0.83
    breaking
    -0.76
    broken
    -0.72
    osponsors
    -0.70
    GE
    -0.70
    break
    -0.70
    idity
    -0.69
    vous
    -0.68
     Myster
    -0.67
    hement
    -0.66
    POSITIVE LOGITS
     Osw
    0.85
     juxtap
    0.77
     emot
    0.77
    unct
    0.73
    agus
    0.70
    assium
    0.67
    ç·
    0.66
    ICS
    0.65
    express
    0.65
    ãĥ¤
    0.65
    Activations Density 0.027%

    No Known Activations