© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 11-RES-JB
    6. 7691
    Prev
    Next
    INDEX
    Explanations

    instances where a decision was made based on appropriateness or necessity

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of "it was" phrases in various contexts

    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
    avia
    -0.67
     beginnings
    -0.66
    ãĥ¯
    -0.65
     understatement
    -0.63
     EVEN
    -0.60
     Drops
    -0.59
    lez
    -0.58
    brates
    -0.57
    Progress
    -0.57
     caveats
    -0.56
    POSITIVE LOGITS
     cheaper
    1.00
     convenient
    0.94
     inconvenient
    0.93
     perceived
    0.86
     safer
    0.83
     easier
    0.81
     Skydragon
    0.79
     cumbers
    0.77
     cheap
    0.77
     prohib
    0.74
    Activations Density 0.377%

    No Known Activations