© 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. 9491
    Prev
    Next
    INDEX
    Explanations

    references to the name "Kojima," potentially related to the famous video game designer Hideo Kojima

    oai_token-act-pair · gpt-3.5-turbo

    frequent mentions of specific individuals or characters, particularly those with the surname "Kojak."

    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
    ield
    -0.68
    STATE
    -0.65
    antha
    -0.62
     Toast
    -0.60
     Oaks
    -0.60
    erences
    -0.60
    APE
    -0.60
     Operator
    -0.59
    yer
    -0.58
     heck
    -0.58
    POSITIVE LOGITS
    tek
    0.89
    mos
    0.82
    inks
    0.77
    isl
    0.76
    ima
    0.75
    anski
    0.68
    isan
    0.67
    ansky
    0.67
    olic
    0.67
    cript
    0.66
    Activations Density 0.091%

    No Known Activations