© 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. 7718
    Prev
    Next
    INDEX
    Explanations

    words related to high technology and specifications

    oai_token-act-pair · gpt-3.5-turbo

    references to "ultra" or high-quality products and technologies

    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
    ilage
    -0.70
     equally
    -0.68
     Learns
    -0.63
    ez
    -0.62
    osuke
    -0.61
     Pon
    -0.61
     entirely
    -0.60
     outright
    -0.59
    tz
    -0.59
    oured
    -0.59
    POSITIVE LOGITS
    fine
    1.12
    fast
    1.06
    orthodox
    0.96
    ordinary
    0.91
    thodox
    0.87
    Fine
    0.87
     violet
    0.86
    high
    0.85
    expensive
    0.83
    charged
    0.80
    Activations Density 0.027%

    No Known Activations