INDEX

Explanations

the usage, complexity, and evolution of language in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 7-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_7/width_16k/average_l0_69

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.7.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

+#+#

-0.69

mybatisplus

-0.63

 nakalista

-0.59

 quæ

-0.57

 EconPapers

-0.57

GEBURTSDATUM

-0.56

findpost

-0.56

 оригіналу

-0.56

 fubject

-0.55

 beginnetje

-0.55

POSITIVE LOGITS

 words

1.13

 terminology

1.03

 Words

1.00

Words

0.99

 WORDS

0.95

 vocabulary

0.94

 terms

0.87

 phrases

0.86

words

0.84

 language

0.81

Activations Density 0.245%

the usage, complexity, and evolution of language in various contexts

No Comments

No Known Activations