INDEX

Explanations

superlative adjectives and terms of distinction

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 25-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_25/width_16k/average_l0_116

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.25.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

Entire

-0.58

Semitism

-0.56

veness

-0.51

 odpowied

-0.50

 Secondly

-0.49

 ogóle

-0.49

one

-0.48

Second

-0.48

 chacune

-0.48

Secondly

-0.48

POSITIVE LOGITS

few

1.24

 many

1.06

 earliest

0.99

few

0.98

 nicest

0.92

 most

0.92

 oldest

0.90

FEW

0.89

Few

0.89

 funniest

0.87

Activations Density 0.185%

superlative adjectives and terms of distinction

No Comments

No Known Activations