INDEX

Explanations

references to links within a code or documentation context

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.5.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

 disambiguazione

-0.73

 समीक्षाओं

-0.72

djangoproject

-0.70

webElement

-0.69

 Italijani

-0.63

 PopupWindow

-0.63

 createSlice

-0.62

 nakalista

-0.62

abestanden

-0.60

 unknownFields

-0.60

POSITIVE LOGITS

link

1.45

Link

1.13

LINK

1.07

 Link

1.04

 link

0.98

 cref

0.95

 LINK

0.86

__(/*!

0.83

リンク

0.71

linking

0.69

Activations Density 0.034%

references to links within a code or documentation context

No Comments

No Known Activations