INDEX

Explanations

phrases related to serious studies or assessments, particularly in scientific or medical contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 17-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_17/width_16k/average_l0_77

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.17.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

 Majefty

-1.03

 pleaſure

-0.97

 purpoſe

-0.94

 houſe

-0.93

 fubject

-0.93

 Monfieur

-0.91

 Jefus

-0.90

 myſelf

-0.88

 ſtate

-0.86

 Reſ

-0.85

POSITIVE LOGITS

 considerable

0.69

 certain

0.67

”

0.59

es

0.59

 multiple

0.56

 very

0.55

 more

0.55

 access

0.54

Activations Density 0.316%

phrases related to serious studies or assessments, particularly in scientific or medical contexts

No Comments

No Known Activations