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

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 8-RES-JB
    6. 9244
    Prev
    Next
    INDEX
    Explanations

    the phrase "without a" followed by specific circumstances or conditions

    oai_token-act-pair · gpt-3.5-turbo

    the phrase "without a" followed by various nouns

    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
    almost
    -0.74
    Links
    -0.70
    unknown
    -0.68
    Mis
    -0.66
    Art
    -0.66
    alian
    -0.66
    Contents
    -0.65
    Adapt
    -0.65
    bec
    -0.64
    Inf
    -0.64
    POSITIVE LOGITS
     dime
    1.19
     satisfactory
    1.13
     lot
    1.10
     clue
    1.08
     single
    1.05
     meaningful
    1.00
     coherent
    1.00
     slightest
    0.99
     definitive
    0.98
     proper
    0.97
    Activations Density 0.217%

    No Known Activations