INDEX

Explanations

references to subscription services and newsletters

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.5.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

 שוליים

-0.85

venger

-0.84

########.

-0.83

ESSOR

-0.81

ⓧ

-0.79

WebElementEntity

-0.76

حوالہ

-0.74

addGap

-0.73

Personendaten

-0.73

 estimés

-0.72

POSITIVE LOGITS

 subscription

2.25

 subscriptions

2.20

 subscribe

2.11

 subscri

1.97

 Subscription

1.93

 subscribed

1.88

 subscribing

1.88

 Subscriptions

1.86

subscription

1.85

 Subscribe

1.77

Activations Density 0.086%

references to subscription services and newsletters

No Comments

No Known Activations