© 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. 0-RES-JB
    6. 15574
    Prev
    Next
    INDEX
    Explanations

    words related to specific locations or countries ending in 'istan'

    oai_token-act-pair · gpt-3.5-turbo

    references to regions or entities associated with 'istan'

    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
     bottle
    -0.64
     HL
    -0.64
     console
    -0.64
     delaying
    -0.63
     attribute
    -0.60
     Mou
    -0.60
     supporting
    -0.60
     bottles
    -0.59
     Fox
    -0.59
     useful
    -0.58
    POSITIVE LOGITS
    istan
    4.89
    istani
    2.69
    stan
    1.34
    zai
    1.15
     Persia
    1.14
    abad
    1.10
    oslov
    1.08
    ornia
    1.08
     Karachi
    1.07
    Pakistan
    1.06
    Activations Density 0.012%

    No Known Activations