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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 2779
    Prev
    Next
    INDEX
    Explanations

    the word "Still" as a signal of continuation or persistence in a series of actions or events

    oai_token-act-pair · gpt-3.5-turbo

    consistent phrases that indicate persistence or ongoing actions

    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
    EGIN
    -0.71
    Course
    -0.70
    ASE
    -0.70
    arthed
    -0.68
    Firstly
    -0.64
    incial
    -0.63
    ufact
    -0.63
    ailand
    -0.62
    atis
    -0.61
    Unit
    -0.60
    POSITIVE LOGITS
    birth
    1.15
     reeling
    1.05
     unsure
    0.92
     unanswered
    0.90
     undecided
    0.89
    born
    0.86
     unresolved
    0.85
     unclear
    0.81
     wondering
    0.80
     unexplained
    0.80
    Activations Density 0.021%

    No Known Activations