INDEX

Explanations

instances of the word "never."

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.20.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

TypedDataSet

-0.91

:]:

-0.84

dafx

-0.83

StateToProps

-0.80

]$}

-0.79

mui

-0.78

 Majefty

-0.78

 kasarigan

-0.77

ConstraintMaker

-0.76

makeConstraints

-0.76

POSITIVE LOGITS

 really

0.73

 never

0.68

 again

0.68

never

0.67

 truly

0.67

 NEVER

0.66

ending

0.64

 Never

0.63

 EVER

0.62

 sekal

0.61

Activations Density 0.057%

instances of the word "never."

No Comments

No Known Activations