INDEX

Explanations

words indicating roles, responsibilities, or actions related to managing and improving practices

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.12.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

ագրություններ

-0.68

Cyfeiriadau

-0.66

DoubleQuotes

-0.65

ItemBackground

-0.61

eradish

-0.60

 >=",

-0.58

 мәкал

-0.57

تقاوى

-0.56

matchCondition

-0.55

 NSCoder

-0.55

POSITIVE LOGITS

Kaieteur

0.61

何より

0.59

TagHelper

0.59

 autorytatywna

0.58

FunctionFlags

0.57

 /\.(

0.55

hankelijk

0.55

 persino

0.54

 even

0.53

 crossorigin

0.53

Activations Density 0.337%

words indicating roles, responsibilities, or actions related to managing and improving practices

No Comments

No Known Activations