© 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. 2176
    Prev
    Next
    INDEX
    Explanations

    email related terms and maybe some numerical and coding references

    oai_token-act-pair · gpt-3.5-turbo

    subjects and topics related to financial transactions and reports

    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
     Ukrain
    -0.87
    Uk
    -0.82
    zbollah
    -0.81
    Sov
    -0.79
    NZ
    -0.78
    hend
    -0.77
     donkey
    -0.76
    Gb
    -0.76
    otonin
    -0.76
     Hezbollah
    -0.72
    POSITIVE LOGITS
     Cal
    2.64
    Cal
    2.34
     cal
    2.09
    cal
    1.92
     CAL
    1.87
     Californ
    1.30
     Calgary
    1.23
     Calder
    1.21
     California
    1.19
     CA
    1.18
    Activations Density 0.160%

    No Known Activations