© 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. 1-RES-JB
    11. 10215
    Prev
    Next
    INDEX
    Explanations

    instances of the word "standing" and its variations

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "standing" and its variations in different contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ramid
    -0.66
     narrowing
    -0.64
    uters
    -0.63
    inia
    -0.62
     pyramid
    -0.61
    apist
    -0.60
    onics
    -0.60
     fragmented
    -0.59
     calming
    -0.58
    omet
    -0.58
    POSITIVE LOGITS
    standing
    1.29
    BuyableInstoreAndOnline
    0.94
    DragonMagazine
    0.92
    theless
    0.89
    owship
    0.81
    ionage
    0.77
    ength
    0.76
    through
    0.74
    Magikarp
    0.73
    _-
    0.73
    Activations Density 0.007%

    No Known Activations