INDEX

Explanations

concepts related to similarities and comparisons

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 19-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_19/width_16k/average_l0_73

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.19.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

 chi̍t

-0.65

 Paglinawan

-0.59

 EconPapers

-0.57

RegistryLite

-0.56

 kasarigan

-0.56

 abstrait

-0.54

 greateſt

-0.53

 ſtate

-0.51

 ordinaires

-0.51

исленность

-0.51

POSITIVE LOGITS

 lines

2.04

 Lines

1.73

lines

1.63

 LINES

1.63

Lines

1.56

LINES

1.27

 line

1.21

 líneas

1.17

 Line

1.10

 lignes

1.09

Activations Density 0.199%

concepts related to similarities and comparisons

No Comments

No Known Activations