© 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. 13849
    Prev
    Next
    INDEX
    Explanations

    geographical locations and sequences that indicate the start and end of something

    oai_token-act-pair · gpt-3.5-turbo

    the word "and" and its various uses in different contexts

    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
    bies
    -0.81
    utch
    -0.75
    20439
    -0.71
    ullivan
    -0.65
    chn
    -0.65
    kee
    -0.64
    onest
    -0.62
    edia
    -0.61
    ogenous
    -0.60
    acus
    -0.59
    POSITIVE LOGITS
     culmin
    1.31
     culminating
    1.27
     gradually
    1.27
     progressing
    1.24
     progresses
    1.23
     ends
    1.22
     ending
    1.20
     progressed
    1.16
     progressively
    1.10
     escal
    1.09
    Activations Density 0.188%

    No Known Activations