© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 11-RES-JB
    11. 20590
    Prev
    Next
    INDEX
    Explanations

    phrases instructing actions or requests with regards to viewing all items

    oai_token-act-pair · gpt-3.5-turbo

    the word "all" in various contexts

    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
    cember
    -0.64
     fatty
    -0.63
    sofar
    -0.62
     somew
    -0.60
    illac
    -0.60
     distingu
    -0.59
    ovember
    -0.58
    raviolet
    -0.58
    heit
    -0.57
     sleeper
    -0.57
    POSITIVE LOGITS
     New
    0.80
    Subscribe
    0.68
    New
    0.67
    IES
    0.65
     è£ıè
    0.63
     Limits
    0.62
     Gallup
    0.62
    äºĶ
    0.61
     Loading
    0.60
    MSN
    0.60
    Activations Density 0.023%

    No Known Activations