INDEX

Explanations

mentions of trips or travel experiences

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

</thead>

-0.90

 Bracken

-0.81

ModelAttribute

-0.77

]**

-0.70

 Samuels

-0.70

ABASES

-0.69

 humaine

-0.68

icestershire

-0.68

 Kell

-0.67

তথ্যসূত্র

-0.67

POSITIVE LOGITS

 trip

2.06

 trips

1.86

trip

1.78

 Trips

1.74

 Trip

1.72

Trip

1.63

trips

1.58

 TRIP

1.57

Trips

1.48

TRIP

1.36

Activations Density 0.051%

mentions of trips or travel experiences

No Comments

No Known Activations