© 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. 6-RES-JB
    11. 17111
    Prev
    Next
    INDEX
    Explanations

    references to software or programming implementations

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "implementation" in various contexts, particularly in technical or programming discussions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    onna
    -0.81
    ovies
    -0.75
    azines
    -0.74
    thur
    -0.69
    ieri
    -0.69
     Gaia
    -0.67
     palms
    -0.64
    otics
    -0.63
    llular
    -0.62
    ids
    -0.62
    POSITIVE LOGITS
     thereof
    0.89
    plementation
    0.88
    eers
    0.82
    eer
    0.81
    eering
    0.80
     implementation
    0.77
     implementations
    0.74
    ãĤ´
    0.74
    alled
    0.72
     implemented
    0.71
    Activations Density 0.031%

    No Known Activations