INDEX

Explanations

conditional phrases expressing possibility or hypothetical scenarios

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 15-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_15/width_16k/average_l0_78

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.15.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

 Ennis

-0.82

 Lipa

-0.81

 kasarigan

-0.79

 Adair

-0.77

ij

-0.74

 Schrader

-0.71

 Roswell

-0.70

 swans

-0.70

GSC

-0.67

 Ciro

-0.66

POSITIVE LOGITS

 WOULD

1.10

ULD

1.09

 would

1.06

 Would

1.05

Would

1.03

_^

0.92

would

0.91

 tartalomajánló

0.90

ould

0.86

ifdef

0.85

Activations Density 0.111%

conditional phrases expressing possibility or hypothetical scenarios

No Comments

No Known Activations