INDEX

Explanations

numerical values associated with various data points or metrics

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 4-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_4/width_16k/average_l0_124

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.4.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

دانشنامهٔ

-0.64

WindowConstants

-0.63

AccessorTable

-0.63

 tartalomajánló

-0.62

 مشين

-0.61

+#+#

-0.59

 neceff

-0.58

Geografi

-0.58

nî

-0.57

 CanadaChoose

-0.57

POSITIVE LOGITS

BeginContext

0.91

__(/*!

0.74

FirebaseDatabase

0.56

Ama

0.55

NOPQRST

0.53

esco

0.53

}:${

0.53

Nin

0.53

kulu

0.52

rdquo

0.52

Activations Density 0.082%

numerical values associated with various data points or metrics

No Comments

No Known Activations

numerical values associated with various data points or metrics

No Comments

No Known Activations