© 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. 10-RES-JB
    11. 3123
    Prev
    Next
    INDEX
    Explanations

    names of individuals and locations

    oai_token-act-pair · gpt-3.5-turbo

    proper nouns, particularly names of people

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    querque
    -0.74
     prostate
    -0.65
    idated
    -0.63
    ãĥIJ
    -0.61
    Magikarp
    -0.61
    heddar
    -0.61
    è¦ļéĨĴ
    -0.61
    ogun
    -0.60
    emetery
    -0.59
     newcom
    -0.59
    POSITIVE LOGITS
     herself
    1.90
     Devi
    1.13
     she
    0.99
    eva
    0.93
     gigg
    0.93
     her
    0.92
     miscar
    0.92
     She
    0.90
    she
    0.90
     Kardashian
    0.89
    Activations Density 0.263%

    No Known Activations