INDEX

Explanations

references to programming-related terms and concepts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 0-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_0/width_16k/average_l0_105

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.0.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

wanda

-0.47

gnus

-0.46

Vol

-0.43

 مقد

-0.43

 title

-0.42

 exist

-0.42

 local

-0.41

 volantes

-0.41

ťaž

-0.41

 existing

-0.41

POSITIVE LOGITS

 betweenstory

1.21

MigrationBuilder

1.13

tagHelperRunner

1.08

 виправивши

1.01

expandindo

0.95

writeFieldEnd

0.93

 समीक्षक

0.92

aarrggbb

0.92

DoubleQuotes

0.89

ArrowToggle

0.88

Activations Density 2.795%

references to programming-related terms and concepts

No Comments

No Known Activations