INDEX

Explanations

first-person and second-person pronouns and their usage in conversational contexts

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

ynb

-0.61

StackNavigator

-0.55

PROLOG

-0.52

 createContext

-0.51

 isNameExpr

-0.50

ItemGroup

-0.49

+#+#

-0.48

volen

-0.48

onOptions

-0.47

UPI

-0.47

POSITIVE LOGITS

ValueStyle

0.65

 just

0.62

>{@

0.62

 powiedzieć

0.60

 wanna

0.59

<bos>

0.59

 Just

0.58

 '\\;'

0.58

AddTagHelper

0.57

sizeCache

0.57

Activations Density 0.164%

first-person and second-person pronouns and their usage in conversational contexts

No Comments

No Known Activations