© 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. 3-RES-JB
    11. 3009
    Prev
    Next
    INDEX
    Explanations

    phrases related to narrowness or limited scope

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "narrow" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ICAN
    -0.80
     Athlet
    -0.76
    natureconservancy
    -0.76
    CF
    -0.74
    IRED
    -0.74
    Gener
    -0.72
     Destruction
    -0.70
     Abuse
    -0.69
    FORE
    -0.69
    IAN
    -0.68
    POSITIVE LOGITS
     narrow
    1.04
    sided
    0.93
     minded
    0.92
    creen
    0.90
     confines
    0.90
    sighted
    0.83
     margins
    0.82
     narrowing
    0.81
     pane
    0.80
    minded
    0.80
    Activations Density 0.009%

    No Known Activations