© 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. 10-RES-JB
    11. 20667
    Prev
    Next
    INDEX
    Explanations

    phrases related to significant actions or changes, such as shutting down a service or quitting a band

    oai_token-act-pair · gpt-3.5-turbo

    references to closure or termination of services, programs, or activities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ested
    -0.62
     ingenuity
    -0.60
    IBLE
    -0.60
    emonic
    -0.58
    ible
    -0.58
    hidden
    -0.57
     convergence
    -0.57
    igree
    -0.57
     molded
    -0.57
    >)
    -0.57
    POSITIVE LOGITS
     altogether
    1.82
     entirely
    1.39
     abruptly
    1.36
     indefinitely
    1.34
     prematurely
    1.28
     temporarily
    1.07
     citing
    1.07
     permanently
    1.05
     due
    1.05
     outright
    1.02
    Activations Density 0.491%

    No Known Activations