INDEX

Explanations

phrases that indicate comparison or contrast

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

 Sapp

-0.80

 Legendre

-0.80

 Athenians

-0.78

 ſtate

-0.76

 itſelf

-0.74

 purpoſe

-0.73

 Pliny

-0.72

 Ptole

-0.72

 himſelf

-0.71

 Thebes

-0.71

POSITIVE LOGITS

 مرئيه

0.79

 MainAxisSize

0.77

 sondern

0.76

EndGlobalSection

0.75

']=='

0.73

 THAN

0.73

oredCriteria

0.73

0.72

tinyos

0.72

 versus

0.72

Activations Density 0.087%

phrases that indicate comparison or contrast

No Comments

No Known Activations