INDEX

Explanations

terms related to resolution in a technical context

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.20.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 "..\..\

-0.68

Hozzáférés

-0.66

BeginContext

-0.66

 useAppContext

-0.64

ramienta

-0.63

QMetaType

-0.63

 Walkover

-0.62

DotNetBar

-0.62

abancı

-0.61

 "..\..\..\

-0.60

POSITIVE LOGITS

 bağlantılar

0.83

 للاسماء

0.65

SMD

0.58

 šal

0.58

 pras

0.57

Ủ

0.54

idän

0.54

chid

0.52

esgue

0.52

 miras

0.50

Activations Density 0.140%

terms related to resolution in a technical context

No Comments

No Known Activations