INDEX

Explanations

the word "more" in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 13-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_13/width_16k/average_l0_84

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.13.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

Discografia

-0.76

️

-0.75

 africana

-0.74

(&:

-0.72

❥

-0.72

__()

-0.71

bufio

-0.69

ⓘ

-0.69

 РФ

-0.68

SNL

-0.67

POSITIVE LOGITS

 more

1.61

 MORE

1.48

more

1.41

MORE

1.39

 More

1.34

More

1.33

 Moreno

1.18

emore

1.09

 than

1.07

 Moreira

1.04

Activations Density 0.128%

the word "more" in various contexts

No Comments

No Known Activations