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. 8551
    Prev
    Next
    INDEX
    Explanations

    instances of the word 'Re'

    oai_token-act-pair · gpt-3.5-turbo

    references to the name "Re."

    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
    ãģĨ
    -0.67
     GEAR
    -0.64
     circuits
    -0.62
    ãĤĬ
    -0.62
    IED
    -0.62
     AAA
    -0.60
     backdrop
    -0.58
     blah
    -0.56
     comr
    -0.56
     NEC
    -0.54
    POSITIVE LOGITS
    becca
    1.37
    ceived
    1.33
    asons
    1.27
    ggie
    1.24
    ck
    1.23
    utsche
    1.22
    efer
    1.21
    verend
    1.21
    ality
    1.19
    venue
    1.15
    Activations Density 0.033%

    No Known Activations