INDEX

Explanations

terms related to directional positioning such as "left" and "right"

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 11-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_11/width_16k/average_l0_80

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.11.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

{§

-0.90

tagext

-0.84

Composable

-0.84

MemoryWarning

-0.78

$_['

-0.77

 FishBase

-0.77

WireFormatLite

-0.76

+:+

-0.75

getInstance

-0.75

abstractmethod

-0.75

POSITIVE LOGITS

left

1.35

 left

1.35

 Left

1.34

Left

1.29

 LEFT

1.25

LEFT

1.24

getLeft

1.15

setLeft

1.12

 esquerdo

1.07

 izquierdo

1.03

Activations Density 0.081%

terms related to directional positioning such as "left" and "right"

No Comments

No Known Activations