© 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. 10652
    Prev
    Next
    INDEX
    Explanations

    references related to geographical locations or names with the word "Mend" in them

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the name "Mend" and related variations in the text

    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
    ngth
    -0.84
    Leary
    -0.67
    ãģĦ
    -0.67
     pneum
    -0.66
    OAD
    -0.66
     menstru
    -0.66
     bowel
    -0.65
    pants
    -0.65
     backpack
    -0.63
    velt
    -0.62
    POSITIVE LOGITS
    enh
    1.10
    ez
    0.97
    els
    0.93
    ell
    0.92
    ele
    0.91
    elson
    0.91
    esian
    0.88
    ragon
    0.88
    iola
    0.87
    rov
    0.87
    Activations Density 0.024%

    No Known Activations