© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 578
    Prev
    Next
    INDEX
    Explanations

    the word part "aker"

    oai_token-act-pair · gpt-4-turbo

    the word "aker" with various prefixes and suffixes

    oai_token-act-pair · gpt-3.5-turbo

    references to the brand Quaker Oats

    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
     malaria
    -0.62
     vicinity
    -0.62
     pall
    -0.60
     haste
    -0.58
     1939
    -0.55
     deadliest
    -0.55
     athe
    -0.55
     goal
    -0.55
     appendix
    -0.54
     troops
    -0.54
    POSITIVE LOGITS
    loo
    1.15
    akers
    1.02
    aker
    0.98
    idge
    0.89
    Maker
    0.83
    ook
    0.82
    ernel
    0.82
    iffe
    0.81
    meier
    0.80
    sonian
    0.80
    Activations Density 0.011%

    No Known Activations