INDEX

Explanations

repeated references to contacting or reaching out to a specific entity, likely in a customer service context

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

 paran

-0.77

 Baillargeon

-0.72

 Rine

-0.70

 Olimpia

-0.68

 Bant

-0.67

 Confe

-0.65

pó

-0.65

 Dign

-0.64

derry

-0.64

COB

-0.64

POSITIVE LOGITS

us

3.01

Us

1.96

Us

1.58

 ourselves

1.56

 нами

1.51

 нам

1.50

me

1.49

our

1.46

 нас

1.41

we

1.39

Activations Density 0.028%

repeated references to contacting or reaching out to a specific entity, likely in a customer service context

No Comments

No Known Activations