INDEX

Explanations

programming elements related to chat applications and user interfaces

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

vaadin

-0.45

[/

-0.43

Dış

-0.43

BASEPATH

-0.43

ma

-0.42

точ

-0.42

ANTLR

-0.41

err

-0.41

 getopt

-0.41

onge

-0.41

POSITIVE LOGITS

zaamheid

0.65

 stället

0.63

 biografias

0.62

НИК

0.62

 cherchés

0.61

 reasonableness

0.61

 Merrick

0.60

 Antiquities

0.59

 constancy

0.59

 peines

0.57

Activations Density 0.064%

programming elements related to chat applications and user interfaces

No Comments

No Known Activations