© 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. 10-RES-JB
    11. 3092
    Prev
    Next
    INDEX
    Explanations

    statements or opinions from various individuals or sources

    oai_token-act-pair · gpt-3.5-turbo

    actions or observations related to decision-making and commentary

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     nig
    -0.74
    definition
    -0.68
     ILCS
    -0.67
    soever
    -0.64
     selves
    -0.63
    Phys
    -0.59
     erase
    -0.58
    relative
    -0.57
    ãĥİ
    -0.57
     footprint
    -0.57
    POSITIVE LOGITS
     herself
    0.86
     himself
    0.85
     eloqu
    0.73
     his
    0.70
     succinct
    0.69
     gloom
    0.69
     plaint
    0.66
     aloud
    0.66
     HuffPost
    0.65
     incred
    0.64
    Activations Density 0.343%

    No Known Activations