INDEX

Explanations

references to deception and manipulation in narratives

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 8-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_8/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.8.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

 виправивши

-0.82

 DOWNVOTE

-0.76

__":

-0.75

Efq

-0.72

 GetEnumerator

-0.71

 CHtml

-0.67

MoveNext

-0.67

 nakalista

-0.66

messageInfo

-0.66

Хочу

-0.66

POSITIVE LOGITS

 pretend

0.58

 pretended

0.53

 pretending

0.52

enumi

0.49

 pretends

0.48

フリ

0.47

囗

0.45

 falsely

0.45

mockito

0.44

 fake

0.44

Activations Density 0.277%

references to deception and manipulation in narratives

No Comments

No Known Activations