© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 11-RES-JB
    6. 1334
    Prev
    Next
    INDEX
    Explanations

    proper nouns related to the name "Nar"

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the term "Nar" in various contexts, likely related to narcotics or a specific narrative theme

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    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
    UCT
    -0.84
    eous
    -0.66
     Pixie
    -0.63
     Athe
    -0.62
     Giuliani
    -0.60
     FG
    -0.60
    ed
    -0.59
    âĦ¢:
    -0.59
     Hots
    -0.59
    e
    -0.58
    POSITIVE LOGITS
    vae
    1.38
    ration
    1.18
    ayan
    1.01
    wh
    0.96
    opa
    0.92
    va
    0.87
    acter
    0.84
    iman
    0.83
    sson
    0.82
    vana
    0.82
    Activations Density 0.063%

    No Known Activations