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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    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. 10813
    Prev
    Next
    INDEX
    Explanations

    phrases related to bias or one-sidedness

    oai_token-act-pair · gpt-3.5-turbo

    the concept of bias or partiality in perspectives

    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
     guru
    -0.63
     real
    -0.62
     Kill
    -0.60
     next
    -0.59
     command
    -0.59
     recogn
    -0.58
     clean
    -0.58
     present
    -0.57
     detection
    -0.57
     IM
    -0.56
    POSITIVE LOGITS
    sided
    4.50
     sided
    2.38
    tailed
    1.68
    faced
    1.33
    dimensional
    1.29
    side
    1.27
    edged
    1.26
    footed
    1.24
    handed
    1.15
    eared
    1.09
    Activations Density 0.013%

    No Known Activations