INDEX

Explanations

positive adjectives and expressions of admiration

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.12.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

SequentialGroup

-0.76

ScopeManager

-0.60

ContentAsync

-0.58

endpush

-0.57

常用

-0.56

 contrario

-0.52

mux

-0.51

iliary

-0.51

 firmer

-0.50

வு

-0.49

POSITIVE LOGITS

 amazing

1.39

amazing

1.38

Amazing

1.32

 feats

1.29

 incredible

1.28

 stupendous

1.27

AMAZING

1.25

Incredible

1.22

 Amazing

1.22

 Impressive

1.21

Activations Density 0.210%

positive adjectives and expressions of admiration

No Comments

No Known Activations