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. 10-RES-JB
    6. 613
    Prev
    Next
    INDEX
    Explanations

    words related to physical trauma or impact

    oai_token-act-pair · gpt-3.5-turbo

    terms related to extreme weather events and climate issues

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     indo
    -0.61
    STAR
    -0.59
     polyg
    -0.58
    avorite
    -0.58
     Bureau
    -0.58
     payable
    -0.56
     stink
    -0.56
    ADRA
    -0.55
     ellipt
    -0.55
     racket
    -0.55
    POSITIVE LOGITS
    ting
    2.20
    ts
    2.09
    ted
    1.88
    ters
    1.83
    ments
    1.64
    ter
    1.61
    te
    1.54
    tted
    1.51
    tes
    1.48
    ty
    1.46
    Activations Density 0.259%

    No Known Activations