Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlog/PodcastSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlog/PodcastGitHubSlackTwitterContact
    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. 14241
    Prev
    Next
    INDEX
    Explanations

    specific Turkish words

    oai_token-act-pair · gpt-3.5-turbo

    references to specific locations or entities, particularly in Istanbul

    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
     Diamond
    -0.74
     Explorer
    -0.70
     Cruise
    -0.66
     explorer
    -0.65
     Bounty
    -0.64
     Off
    -0.64
     Misc
    -0.64
     Liberty
    -0.62
     Powers
    -0.62
     Juno
    -0.61
    POSITIVE LOGITS
    ÅŁ
    4.51
    ÄŁ
    4.09
    Äĩ
    2.36
    ÅĤ
    2.34
    Å¡
    2.33
    ÃŁ
    2.18
    È
    2.15
    ç
    2.05
    oÄŁ
    1.96
    Äį
    1.93
    Activations Density 0.028%

    No Known Activations