INDEX

Explanations

phrases or structures that include variations of the word "as"

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 11-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_11/width_16k/average_l0_80

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.11.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

 itſelf

-1.07

 raiſ

-1.03

ſelf

-0.98

 pleaſure

-0.98

 Houſe

-0.95

 houſe

-0.95

 Anſ

-0.91

 Reſ

-0.91

 ſever

-0.91

 Conſ

-0.90

POSITIVE LOGITS

As

1.25

AS

1.23

as

1.16

As

1.11

readAs

1.04

AS

0.87

as

0.82

 CreateTagHelper

0.77

0.75

follows

0.73

Activations Density 0.362%

phrases or structures that include variations of the word "as"

No Comments

No Known Activations