© 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. 1-RES-JB
    11. 3277
    Prev
    Next
    INDEX
    Explanations

    locations or names related to countries

    oai_token-act-pair · gpt-3.5-turbo

    references to the regions and countries ending with 'istan'

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     gull
    -0.65
    eared
    -0.64
    FACE
    -0.62
     cas
    -0.60
    oké
    -0.59
     payload
    -0.59
     subscriber
    -0.58
     appearances
    -0.58
     disclosure
    -0.58
     stub
    -0.57
    POSITIVE LOGITS
    istan
    1.46
    istani
    0.98
    uates
    0.83
    bia
    0.80
    mA
    0.79
    ghan
    0.77
     Hussein
    0.77
    oglu
    0.76
    ãĤ¿
    0.76
    aroo
    0.75
    Activations Density 0.007%

    No Known Activations