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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 8-RES-JB
    6. 17752
    Prev
    Next
    INDEX
    Explanations

    phrases containing the word "Be"

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the word "Be" or variations thereof

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     glide
    -0.66
     Ples
    -0.66
     residue
    -0.65
     orbit
    -0.64
     pole
    -0.63
     drift
    -0.62
     hoops
    -0.61
     portrait
    -0.61
     mash
    -0.60
     excise
    -0.60
    POSITIVE LOGITS
    hemoth
    1.35
    yond
    1.27
    arers
    1.23
    ijing
    1.22
    arer
    1.20
    acons
    1.12
    arded
    1.11
    zos
    1.09
    heading
    1.08
    aum
    1.06
    Activations Density 0.030%

    No Known Activations