© 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. 8-RES-JB
    11. 7300
    Prev
    Next
    INDEX
    Explanations

    phrases related to belonging or being a component of something

    oai_token-act-pair · gpt-3.5-turbo

    references to official statements or parts of various subjects

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     whiff
    -0.69
    wered
    -0.66
    ampires
    -0.66
    adish
    -0.66
     candles
    -0.65
    aughs
    -0.64
     realistically
    -0.63
    Liter
    -0.63
    sers
    -0.62
     prostitutes
    -0.62
    POSITIVE LOGITS
    igsaw
    0.87
     continuum
    0.78
     endeavour
    0.77
    ĸļ
    0.75
     repertoire
    0.74
    yssey
    0.72
     regimen
    0.71
     puzzle
    0.70
     strategy
    0.67
     constellation
    0.67
    Activations Density 0.397%

    No Known Activations