© 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. 2-RES-JB
    11. 1003
    Prev
    Next
    INDEX
    Explanations

    the word "Belt" in the text

    oai_token-act-pair · gpt-4-turbo

    phrases related to physical locations or regions

    oai_token-act-pair · gpt-3.5-turbo

    references to the "Belt" concept, particularly in relation to infrastructure or initiatives

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    å¼
    -0.70
    å£
    -0.68
    ×Ļ×
    -0.67
    chrom
    -0.66
     Qiao
    -0.65
    zanne
    -0.65
    issan
    -0.64
    CHR
    -0.62
     UNIVERS
    -0.61
    EFF
    -0.61
    POSITIVE LOGITS
     Belt
    1.17
    belt
    0.94
    wic
    0.81
    pak
    0.79
    minster
    0.75
    mouth
    0.72
     buckle
    0.71
     mathemat
    0.69
    rants
    0.69
     Lines
    0.69
    Activations Density 0.007%

    No Known Activations