© 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. 4-RES-JB
    11. 15717
    Prev
    Next
    INDEX
    Explanations

    the word "only" in various contexts

    oai_token-act-pair · gpt-3.5-turbo

    phrases emphasizing exclusivity or singularity

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

    No Comments

    Negative Logits
     Carbuncle
    -0.70
    insula
    -0.70
    ategor
    -0.64
    mass
    -0.64
    senal
    -0.64
    align
    -0.63
    aptic
    -0.63
    staking
    -0.62
    idon
    -0.61
    Rs
    -0.61
    POSITIVE LOGITS
     thing
    0.85
     surviving
    0.84
     drawback
    0.84
     recourse
    0.79
     conceivable
    0.78
     remaining
    0.78
     valid
    0.76
     downside
    0.75
     exception
    0.74
     possible
    0.73
    Activations Density 0.034%

    No Known Activations