INDEX

Explanations

terms related to threats or danger

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 6-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_6/width_16k/average_l0_70

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.6.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

unny

-0.72

Absorption

-0.71

addPreferredGap

-0.69

inyin

-0.66

 gustar

-0.66

urator

-0.66

ודם

-0.65

adins

-0.64

abin

-0.64

crisy

-0.62

POSITIVE LOGITS

 threat

2.31

threat

2.22

 Threat

2.19

 threats

2.17

Threat

2.11

 Threats

2.06

 threatened

1.85

Threats

1.83

 threatens

1.78

 threatening

1.76

Activations Density 0.049%

terms related to threats or danger

No Comments

No Known Activations