INDEX

Explanations

pronouns referring to oneself or others, indicating a focus on identity and relationships

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.16.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

WillAppear

-0.77

 '\\;'

-0.75

 ExecuteAsync

-0.74

TypedDataSet

-0.72

SpringBootTest

-0.70

IndentedString

-0.68

MessageOf

-0.65

 kasarigan

-0.65

 Baillargeon

-0.64

rungsseite

-0.63

POSITIVE LOGITS

zelf

0.61

 from

0.60

as

0.58

Πηγή

0.57

 pungkasnya

0.57

self

0.53

 with

0.53

 bowiem

0.51

 disposent

0.51

 sendiri

0.51

Activations Density 0.197%

pronouns referring to oneself or others, indicating a focus on identity and relationships

No Comments

No Known Activations