INDEX

Explanations

terms related to duration or time intervals

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

ar

-0.53

Sar

-0.53

mber

-0.49

por

-0.46

em

-0.45

sur

-0.45

nt

-0.44

-0.43

du

-0.43

POSITIVE LOGITS

 vecka

1.00

migrationBuilder

0.93

parsedMessage

0.91

 שוליים

0.89

 مشين

0.89

 week

0.88

 Woche

0.87

protoimpl

0.86

tvguidetime

0.85

 Мексичка

0.84

Activations Density 0.351%

terms related to duration or time intervals

No Comments

No Known Activations