INDEX

Explanations

repeated proper nouns and specific names

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

GEBURTSDATUM

-0.93

はじめに

-0.74

:✨

-0.74

 بيها

-0.62

+][

-0.61

EndGlobalSection

-0.59

 kasarigan

-0.58

ientôt

-0.58

rungsseite

-0.58

 snippetHide

-0.57

POSITIVE LOGITS

 itself

0.60

 proprement

0.60

 itſelf

0.59

’

0.58

 stessa

0.58

 protoimpl

0.55

0.54

 InputDecoration

0.53

 himſelf

0.53

 stesso

0.52

Activations Density 0.883%

repeated proper nouns and specific names

No Comments

No Known Activations