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. 19596
    Prev
    Next
    INDEX
    Explanations

    actions related to moving and organizing belongings

    oai_token-act-pair · gpt-3.5-turbo

    conjunctions and phrases indicating connected actions or sequences

    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
     Himself
    -0.68
    ansom
    -0.66
    Enlarge
    -0.66
    天
    -0.64
     Recent
    -0.61
    grades
    -0.60
    spons
    -0.59
    NULL
    -0.59
     guiIcon
    -0.58
    far
    -0.57
    POSITIVE LOGITS
     realised
    1.25
     realized
    1.21
     waited
    1.15
     stumbled
    1.14
     watched
    1.12
     forgot
    1.11
     listened
    1.11
     pretended
    1.07
     figured
    1.07
     tried
    1.06
    Activations Density 0.248%

    No Known Activations