INDEX

Explanations

references to corporate entities or organizations

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

 Wheeler

-0.76

 Poster

-0.75

 Waller

-0.70

 mAdapter

-0.69

 fritas

-0.68

<strong>

-0.66

⑦

-0.66

 meglio

-0.65

 Breathe

-0.65

 Peta

-0.64

POSITIVE LOGITS

Inc

1.73

inc

1.71

Inc

1.69

INC

1.63

inc

1.57

INC

1.41

 Incidents

1.21

 incidents

1.18

 Incorporated

1.10

 incidental

1.01

Activations Density 0.086%

references to corporate entities or organizations

No Comments

No Known Activations