© 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. 18628
    Prev
    Next
    INDEX
    Explanations

    contrasting statements that counter an expected outcome

    oai_token-act-pair · gpt-3.5-turbo

    phrases that contrast one idea with another using "rather."

    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
    ears
    -0.75
    shaw
    -0.74
     Marse
    -0.67
    Sund
    -0.66
    chet
    -0.64
    aund
    -0.64
     Seal
    -0.63
    bell
    -0.63
    iland
    -0.63
    illas
    -0.63
    POSITIVE LOGITS
     Content
    0.77
     "<
    0.74
    ATURES
    0.67
     merely
    0.66
     props
    0.65
     focusing
    0.63
     descript
    0.63
     consisted
    0.63
    pires
    0.62
    =""
    0.62
    Activations Density 0.030%

    No Known Activations