INDEX

Explanations

phrases or words indicating the highest level of quality or achievement

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

one

-0.77

-0.76

her

-0.75

the

-0.60

 more

-0.57

my

-0.57

No

-0.57

 other

-0.56

 some

-0.56

POSITIVE LOGITS

 Monfieur

1.21

 itſelf

1.18

 myſelf

1.15

 himſelf

1.09

 Shakspeare

1.09

 themſelves

1.07

 Theſe

1.05

 ―――――

1.04

 againſt

1.00

 Elsewhere

0.99

Activations Density 0.469%

phrases or words indicating the highest level of quality or achievement

No Comments

No Known Activations