© 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. 4-RES-JB
    11. 384
    Prev
    Next
    INDEX
    Explanations

    countries and specific natural elements

    oai_token-act-pair · gpt-3.5-turbo

    geographic locations and their related contexts

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

    No Comments

    Negative Logits
    htaking
    -0.62
    Pg
    -0.55
    20439
    -0.50
     Samar
    -0.50
    nai
    -0.49
    uthor
    -0.49
    oubted
    -0.49
    baugh
    -0.47
    orah
    -0.47
    ï¸ı
    -0.47
    POSITIVE LOGITS
     equivalents
    0.56
     skelet
    0.50
    rique
    0.49
     rul
    0.46
     nursery
    0.46
     dement
    0.45
    '."
    0.45
     cryst
    0.45
     Ludwig
    0.44
     constitu
    0.44
    Activations Density 3.301%

    No Known Activations