INDEX

Explanations

terms related to literature, theatre, and notable public figures

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.5.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

참고

-0.71

encodeWith

-0.70

 muualla

-0.60

EDEFAULT

-0.60

prüche

-0.59

parsedMessage

-0.59

TargetException

-0.58

Externé

-0.58

原始内容存档于

-0.57

URLException

-0.57

POSITIVE LOGITS

AndEndTag

0.59

HasAnnotation

0.51

 Lump

0.45

marvin

0.44

DoubleQuotes

0.44

 webdriver

0.43

 Yugoslav

0.43

Sof

0.42

 Soap

0.42

INK

0.42

Activations Density 1.972%

terms related to literature, theatre, and notable public figures

No Comments

No Known Activations