INDEX

Explanations

numerical data and indicators with a specific formatting pattern

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

 Feeding

-0.60

ondissement

-0.58

OGND

-0.56

 feeding

-0.53

ateg

-0.53

WireFormatLite

-0.52

_$

-0.52

 propOrder

-0.52

bo

-0.51

AccessorTable

-0.51

POSITIVE LOGITS

 فريبيس

0.74

WebVitals

0.63

 viață

0.61

клопе

0.61

 ThemeData

0.61

ABR

0.60

 alcuna

0.58

 '\\;'

0.58

KommentareTeilen

0.57

 entanto

0.57

Activations Density 0.275%

numerical data and indicators with a specific formatting pattern

No Comments

No Known Activations