© 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. 2-RES-JB
    11. 343
    Prev
    Next
    INDEX
    Explanations

    variations of the word "dodgy" or the beginning syllable "dod" in different contexts

    oai_token-act-pair · gpt-4-turbo

    references to the term "Dodger"

    oai_token-act-pair · gpt-3.5-turbo

    references to the term "Dod" and related variations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ILCS
    -0.88
    _>
    -0.73
    HAHAHAHA
    -0.72
     treason
    -0.70
    inventoryQuantity
    -0.69
    urdue
    -0.68
    ropolitan
    -0.67
    ORTS
    -0.67
    perture
    -0.67
    OWER
    -0.66
    POSITIVE LOGITS
     Dod
    1.08
    gers
    0.99
    gments
    0.97
    yssey
    0.96
    gment
    0.95
    gement
    0.94
    eca
    0.91
    sworth
    0.90
    erick
    0.90
    ifferent
    0.89
    Activations Density 0.006%

    No Known Activations