INDEX

Explanations

references to victims 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 @ 10-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_10/width_16k/average_l0_77

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.10.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

</b>

-0.67

-0.66

 demás

-0.65

шое

-0.61

ⓧ

-0.60

 wireType

-0.60

ведения

-0.58

ronomy

-0.58

REQUIRE

-0.58

尔的

-0.58

POSITIVE LOGITS

 victims

1.86

 Victims

1.67

 Victim

1.51

 victim

1.51

victim

1.39

 victimes

1.38

 victime

1.36

Victim

1.23

 víctimas

1.18

 жерт

1.18

Activations Density 0.112%

references to victims in various contexts

No Comments

No Known Activations