INDEX

Explanations

instances of refusal or denial

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.3.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

رحلة

-0.76

ExtendWith

-0.72

iVar

-0.70

virons

-0.69

xsi

-0.68

uxxxx

-0.68

paux

-0.68

сюда

-0.66

сього

-0.66

odeon

-0.65

POSITIVE LOGITS

 refuse

2.47

 refusal

2.38

 refused

2.35

 refuses

2.34

 refusing

2.33

 Refuse

2.21

 refus

2.07

 refuser

1.70

 refusé

1.66

 menolak

1.32

Activations Density 0.092%

instances of refusal or denial

No Comments

No Known Activations