© 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. 7504
    Prev
    Next
    INDEX
    Explanations

    mentions of specific characters or locations

    oai_token-act-pair · gpt-3.5-turbo

    the specific character sequence 'âĢĭ'

    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
    cius
    -0.89
    otine
    -0.83
    ipal
    -0.80
    pread
    -0.78
    oresc
    -0.75
    ciating
    -0.73
    ffield
    -0.73
    gery
    -0.71
    ulatory
    -0.71
    lihood
    -0.70
    POSITIVE LOGITS
    1.24
    1.21
    1.13
    âĢ¢âĢ¢
    0.98
    âĢ¢âĢ¢âĢ¢âĢ¢
    0.91
    Memory
    0.81
    ¯
    0.79
     âľĶ
    0.78
    Ð
    0.78
    taboola
    0.77
    Activations Density 0.002%

    No Known Activations