INDEX

Explanations

the word "fine" and its variations in different contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 14-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_14/width_16k/average_l0_84

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.14.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

 INTERESAR

-0.85

 McCl

-0.84

 hObject

-0.80

="@+

-0.79

 Heater

-0.75

 Cabot

-0.75

 Renato

-0.74

 Trotz

-0.74

orious

-0.73

 Marcello

-0.72

POSITIVE LOGITS

 Fines

1.02

 fines

0.93

FINE

0.91

mine

0.90

fines

0.90

 Fine

0.89

 fined

0.88

fine

0.85

 Fins

0.85

 FINE

0.81

Activations Density 0.094%

the word "fine" and its variations in different contexts

No Comments

No Known Activations