INDEX

Explanations

occurrences of the word "loop" and related terms

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 13-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_13/width_16k/average_l0_84

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.13.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

 Marcy

-0.68

 esportes

-0.65

𝓵

-0.65

 Hodges

-0.65

 rosse

-0.63

 داری

-0.63

NEC

-0.63

 généraux

-0.62

werfer

-0.61

 Elia

-0.60

POSITIVE LOGITS

 loop

1.23

loop

1.15

 loops

1.13

 LOOP

1.06

 Loop

1.01

tagHelperRunner

0.97

loops

0.96

LOOP

0.94

InputModule

0.94

Loop

0.92

Activations Density 0.248%

occurrences of the word "loop" and related terms

No Comments

No Known Activations