© 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. 0-RES-JB
    11. 14844
    Prev
    Next
    INDEX
    Explanations

    phrases or words related to summons or people's names followed by numbers

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "mons" and its variations within the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     fib
    -0.81
     Fib
    -0.79
     Viet
    -0.77
     widow
    -0.77
    mong
    -0.73
     squid
    -0.72
     torpedo
    -0.72
    istan
    -0.71
     Polly
    -0.70
     Thermal
    -0.67
    POSITIVE LOGITS
    mons
    3.04
    mn
    2.49
     summons
    1.92
    mens
    1.44
    aukee
    1.35
    irs
    1.28
    MN
    1.16
     summoning
    1.10
    mony
    1.05
     Summon
    1.03
    Activations Density 0.029%

    No Known Activations