© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 12-RES-JB
    11. 3706
    Prev
    Next
    INDEX
    Explanations

    the word "ain" repeated at different activation levels

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot

    instances of the substring "ain" within words

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 12-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.hook_resid_post
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    torch.float32
    Hook Point
    blocks.11.hook_resid_post
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ILY
    -0.63
     hive
    -0.58
     mitigating
    -0.57
     sorely
    -0.57
     recy
    -0.56
     holders
    -0.55
     yet
    -0.54
     renew
    -0.54
     adoption
    -0.54
     closest
    -0.53
    POSITIVE LOGITS
    thood
    1.34
    esville
    1.08
    bow
    1.07
    wright
    1.03
    tenance
    1.03
    ey
    0.96
    ese
    0.93
    tell
    0.92
    voy
    0.91
    fo
    0.91
    Activations Density 0.027%

    No Known Activations