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

    Neuronpedia

    APICircuit 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. 6-RES-JB
    6. 15995
    Prev
    Next
    INDEX
    Explanations

    words related to acceleration or escalation

    oai_token-act-pair · gpt-3.5-turbo

    terms related to movement and escalation in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Dragonbound
    -0.79
    beard
    -0.75
     Principle
    -0.71
     Belt
    -0.69
     Maid
    -0.69
     Doctrine
    -0.66
     Primordial
    -0.65
     Shack
    -0.64
     Worldwide
    -0.63
     Hole
    -0.63
    POSITIVE LOGITS
    ators
    1.64
    ator
    1.57
    ates
    1.45
    ations
    1.45
    ational
    1.35
    atory
    1.34
    ating
    1.32
    atable
    1.28
    atorial
    1.28
    ative
    1.26
    Activations Density 0.076%

    No Known Activations