© 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. 10-RES-JB
    11. 10249
    Prev
    Next
    INDEX
    Explanations

    phrases related to making a comparison

    oai_token-act-pair · gpt-3.5-turbo

    phrases that include the word "say."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    stra
    -0.67
     Siber
    -0.60
    olated
    -0.60
    ATURE
    -0.59
     Instruments
    -0.59
    vernight
    -0.58
    olate
    -0.56
    itol
    -0.56
    ļéĨĴ
    -0.55
    peria
    -0.55
    POSITIVE LOGITS
     uh
    1.30
     um
    1.27
     say
    1.15
     oh
    1.08
    say
    1.06
    wait
    1.02
     gasp
    1.01
     ah
    1.01
     well
    0.93
     er
    0.92
    Activations Density 0.096%

    No Known Activations