INDEX

Explanations

words related to assistance and support

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

"help" followed by a verb

np_acts-logits-general · gemini-2.0-flash

help explain or improve

np_acts-logits-general · gemini-2.5-flash-lite

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.22.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

be

-0.63

use

-0.60

Use

-0.59

Be

-0.59

Be

-0.59

Use

-0.58

BE

-0.55

 jeito

-0.49

 Using

-0.48

},{

-0.48

POSITIVE LOGITS

fully

0.92

RenderAtEndOf

0.84

 facilitate

0.84

 propOrder

0.83

Personendaten

0.82

 alleviate

0.80

NOPQRST

0.79

tagext

0.79

AlterField

0.76

haustible

0.76

Activations Density 0.053%

words related to assistance and support

"help" followed by a verb

help explain or improve

No Comments

No Known Activations