INDEX

Explanations

queries expressing a desire to understand or inquire about information

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 0-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_0/width_16k/average_l0_105

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.0.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

-0.68

-0.67

has

-0.63

-0.62

-0.61

-0.56

-0.55

POSITIVE LOGITS

Efq

1.42

 ſeveral

1.16

 Monfieur

1.15

 myſelf

1.13

 itſelf

1.12

 Jefus

1.09

 doubtnut

1.08

 ―――――

1.07

 Majefty

1.06

$_"

1.05

Activations Density 0.341%

queries expressing a desire to understand or inquire about information

No Comments

No Known Activations