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. 11-RES-JB
    6. 15324
    Prev
    Next
    INDEX
    Explanations

    specific pairs of related words or phrases

    oai_token-act-pair · gpt-3.5-turbo

    terms associated with scientific and technical concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ','
    -0.62
    Angelo
    -0.61
    SourceFile
    -0.61
    "]=>
    -0.59
    Brave
    -0.58
    bie
    -0.57
    lished
    -0.56
     et
    -0.56
     and
    -0.55
    uga
    -0.55
    POSITIVE LOGITS
     alike
    1.50
     are
    1.41
     aren
    1.26
     collide
    1.26
     respectively
    1.22
     were
    1.19
     differ
    1.18
     weren
    1.13
     converge
    1.10
     combine
    1.05
    Activations Density 0.425%

    No Known Activations