© 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. 21309
    Prev
    Next
    INDEX
    Explanations

    terms related to the city or region of Erbil

    oai_token-act-pair · gpt-3.5-turbo

    mentions of a specific type of currency or monetary unit

    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
    ered
    -0.70
    rouse
    -0.63
     CNS
    -0.63
    tails
    -0.62
     FIRE
    -0.62
    feature
    -0.61
     OU
    -0.60
     Feature
    -0.60
    Trend
    -0.60
    reme
    -0.58
    POSITIVE LOGITS
    isi
    1.24
    bil
    1.19
    gewater
    0.96
    mingham
    0.95
    ascus
    0.94
    ulent
    0.88
    stanbul
    0.86
    ittle
    0.84
    vest
    0.84
     Lumpur
    0.84
    Activations Density 0.007%

    No Known Activations