INDEX

Explanations

descriptive terms related to readiness and completion in various contexts

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

 eenige

-0.57

essentiel

-0.54

%")

-0.54

 photolibrary

-0.53

 lorry

-0.53

ällor

-0.53

 Hän

-0.53

 propTypes

-0.52

 Sarm

-0.52

 itſelf

-0.52

POSITIVE LOGITS

yet

4.01

yet

3.37

Yet

3.09

Yet

3.04

YET

2.83

 endnu

2.12

 ännu

1.93

 aún

1.62

 todavía

1.61

 jeszcze

1.61

Activations Density 0.377%

descriptive terms related to readiness and completion in various contexts

No Comments

No Known Activations