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. 5-RES-JB
    6. 2406
    Prev
    Next
    INDEX
    Explanations

    phrases related to comparisons and differences

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the character "âĢ" in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 5-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    5
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Kenyan
    -0.65
     blender
    -0.64
     Sicily
    -0.62
     tremend
    -0.62
     whirlwind
    -0.62
     dust
    -0.61
     scattering
    -0.61
     healing
    -0.61
     scatter
    -0.60
     Bohem
    -0.59
    POSITIVE LOGITS
    alone
    0.89
    ihad
    0.81
    ¹
    0.78
    âĹ¼
    0.76
    thus
    0.75
    º
    0.73
    tor
    0.72
    ership
    0.72
    ħ
    0.72
    WER
    0.71
    Activations Density 0.308%

    No Known Activations