© 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. 16411
    Prev
    Next
    INDEX
    Explanations

    words related to countries

    oai_token-act-pair · gpt-3.5-turbo

    references to Sierra Leone

    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
    Els
    -0.70
    Hug
    -0.65
    amy
    -0.64
    Hum
    -0.64
     bitter
    -0.62
    irlf
    -0.61
    aminer
    -0.61
    ifice
    -0.61
    Layer
    -0.60
    model
    -0.60
    POSITIVE LOGITS
     Leone
    1.63
     Outbreak
    0.94
     Liberia
    0.82
    Äĩ
    0.82
     Senegal
    0.80
    vernment
    0.77
     Congo
    0.76
     Lumpur
    0.76
    culosis
    0.75
     Niger
    0.75
    Activations Density 0.004%

    No Known Activations