© 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. 2144
    Prev
    Next
    INDEX
    Explanations

    keywords related to academic articles or research papers

    oai_token-act-pair · gpt-3.5-turbo

    the preposition "on" used in various contexts throughout the text

    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
    YY
    -0.69
    SourceFile
    -0.67
    TY
    -0.66
    Champ
    -0.64
    waters
    -0.63
    à©
    -0.63
     Sabha
    -0.63
    SAY
    -0.62
    ëĭ
    -0.61
    ey
    -0.61
    POSITIVE LOGITS
     behalf
    1.47
    erous
    1.05
    site
    0.96
    sets
    0.88
    yx
    0.87
     topics
    0.85
    shore
    0.84
    etime
    0.80
    eworld
    0.80
     steroids
    0.80
    Activations Density 0.178%

    No Known Activations