INDEX

Explanations

expressions of honesty and straightforwardness

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

=’

-0.64

 étend

-0.63

InvalidProtocol

-0.60

AndWait

-0.59

ană

-0.57

 μέ

-0.54

 spéciaux

-0.54

GEBURTS

-0.54

льше

-0.53

artin

-0.52

POSITIVE LOGITS

Frankly

1.04

Honestly

1.02

 honestly

1.00

 frankly

0.98

 Honestly

0.92

Tbh

0.89

tbh

0.89

honestly

0.83

说实话

0.83

 admit

0.80

Activations Density 0.129%

expressions of honesty and straightforwardness

No Comments

No Known Activations