© 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. 7-RES-JB
    11. 11283
    Prev
    Next
    INDEX
    Explanations

    words related to actions that are ongoing or continuous

    oai_token-act-pair · gpt-3.5-turbo

    action words ending in 'ing'

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    å£
    -0.72
     Leilan
    -0.71
    iever
    -0.67
    irtual
    -0.66
    vier
    -0.66
    luaj
    -0.62
     disarm
    -0.62
    mson
    -0.61
    ensable
    -0.60
    ieving
    -0.60
    POSITIVE LOGITS
    redients
    1.26
    tons
    1.09
    HAM
    0.72
    hots
    0.72
    ales
    0.71
    rates
    0.69
    caps
    0.69
    ulate
    0.69
    lass
    0.68
    atis
    0.68
    Activations Density 0.096%

    No Known Activations