© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 8-RES-JB
    6. 6545
    Prev
    Next
    INDEX
    Explanations

    instances of the word "Villanova."

    oai_token-act-pair · gpt-3.5-turbo

    repeated mentions of the entity "Villanova."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    manship
    -0.75
    çķ
    -0.75
    à¥
    -0.67
    ा
    -0.66
     hypers
    -0.66
     pelvic
    -0.65
    é¾įåĸļ士
    -0.64
     pseud
    -0.63
    ï¸
    -0.62
    ãĥ¼ãĥĨ
    -0.62
    POSITIVE LOGITS
    iage
    1.37
    anova
    1.34
    agers
    1.34
    ains
    1.16
    ages
    1.09
    ain
    1.07
    ager
    1.04
    aine
    1.00
    enge
    0.95
    anders
    0.93
    Activations Density 0.031%

    No Known Activations