© 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. 10846
    Prev
    Next
    INDEX
    Explanations

    phrases related to speed or efficiency

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "quick."

    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
    Ãį
    -0.76
    ichick
    -0.75
    #$#$
    -0.71
    reon
    -0.69
    ickson
    -0.67
    iosyncr
    -0.66
    âĹ¼
    -0.66
    ÃįÃį
    -0.66
    ertodd
    -0.64
     Integrity
    -0.64
    POSITIVE LOGITS
    ened
    1.10
    ening
    1.08
    itude
    1.07
     turnaround
    1.03
     succession
    1.02
    aneously
    0.99
     glance
    0.96
    lime
    0.90
    eners
    0.89
    shot
    0.89
    Activations Density 0.029%

    No Known Activations