INDEX

Explanations

sections of the text that contain numerical data or references to structured information

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.12.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

 acorns

-0.71

 Públicas

-0.57

 Apare

-0.57

 Guilherme

-0.57

ніципа

-0.56

 raisins

-0.55

olsom

-0.53

 cavalo

-0.50

Utt

-0.50

 Ráp

-0.49

POSITIVE LOGITS

TabIndex

5.59

 AssemblyTitle

1.00

脚注の使い方

0.97

twimg

0.94

VersionUID

0.92

TagMode

0.88

 CreateTagHelper

0.88

BufferException

0.86

 مشين

0.81

 MessageBoxIcon

0.81

Activations Density 0.004%

sections of the text that contain numerical data or references to structured information

No Comments

No Known Activations