INDEX

Explanations

references to concepts of being "off," "off-label," or "off" actions in various contexts

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

IMA

-0.89

Życiorys

-0.81

 Wren

-0.81

LabelTagHelper

-0.78

publicKey

-0.77

esgue

-0.76

SqlClient

-0.75

quelize

-0.73

 nahilalakip

-0.73

ณะ

-0.72

POSITIVE LOGITS

Off

1.75

OFF

1.69

off

1.66

Off

1.58

off

1.52

OFF

1.41

 offs

1.29

offs

1.24

 ऑफ

0.94

オフ

0.93

Activations Density 0.050%

references to concepts of being "off," "off-label," or "off" actions in various contexts

No Comments

No Known Activations