© 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. 10580
    Prev
    Next
    INDEX
    Explanations

    phrases related to the concept of "pizza"

    oai_token-act-pair · gpt-3.5-turbo

    references to a particular type of food or dish

    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
     Polar
    -0.68
     appropriation
    -0.68
     NX
    -0.62
     fitness
    -0.61
    fulness
    -0.60
     Malays
    -0.60
     conspicuous
    -0.59
     Koreans
    -0.59
     Korea
    -0.58
    izable
    -0.57
    POSITIVE LOGITS
    arella
    1.44
    etta
    1.21
    erella
    1.09
    olla
    1.00
    ucc
    0.97
    hou
    0.96
    zz
    0.96
    ella
    0.94
    azz
    0.94
    eret
    0.92
    Activations Density 0.027%

    No Known Activations