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. 11-RES-JB
    6. 10525
    Prev
    Next
    INDEX
    Explanations

    terms related to construction or obstruction

    oai_token-act-pair · gpt-3.5-turbo

    terms related to collective actions and structures

    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
     thirds
    -0.74
    butt
    -0.64
    nd
    -0.64
     Peninsula
    -0.62
     bes
    -0.62
    hra
    -0.61
     Teresa
    -0.59
    QUEST
    -0.57
     awake
    -0.57
     Schne
    -0.57
    POSITIVE LOGITS
    ions
    2.43
    ive
    2.23
    ively
    2.05
    ors
    2.03
    ional
    2.03
    ives
    2.03
    ivity
    1.98
    iveness
    1.91
    IONS
    1.85
    ION
    1.85
    Activations Density 0.274%

    No Known Activations