INDEX

Explanations

references to levels, particularly in terms of quality, performance, or other categorical metrics

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 19-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_19/width_16k/average_l0_73

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.19.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

 виправивши

-0.88

انيف

-0.84

")));

-0.83

EDEFAULT

-0.82

 estekak

-0.82

MessageTagHelper

-0.78

CloseOperation

-0.77

 дописавши

-0.74

")){

-0.73

 otomatig

-0.73

POSITIVE LOGITS

 LEVEL

1.02

LEVEL

0.94

 levels

0.93

 Level

0.92

Levels

0.91

level

0.88

 Levels

0.87

levels

0.84

 level

0.84

Level

0.80

Activations Density 0.086%

references to levels, particularly in terms of quality, performance, or other categorical metrics

No Comments

No Known Activations