INDEX

Explanations

words and phrases related to ratings and feedback

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

 تضيفلها

-0.74

in

-0.66

吗

-0.60

ValueStyle

-0.59

estan

-0.59

 known

-0.57

 समीक्षाओं

-0.57

ništ

-0.56

 here

-0.56

simmon

-0.56

POSITIVE LOGITS

 Inſ

0.91

 Reſ

0.90

 ſche

0.89

 auffi

0.87

 ſtate

0.85

 Houſe

0.84

 Diſ

0.83

 dezelve

0.83

 myſelf

0.82

 ſeveral

0.79

Activations Density 0.210%

words and phrases related to ratings and feedback

No Comments

No Known Activations