INDEX

Explanations

references to left and right in a spatial or directional context

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 8-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_8/width_16k/average_l0_71

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.8.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

 transfieras

-0.77

 nonUne

-0.70

Rüyada

-0.66

{?>

-0.66

жели

-0.65

blume

-0.65

 Halter

-0.65

initializeApp

-0.64

깐

-0.63

POSITIVE LOGITS

 left

0.95

 RIGHT

0.95

 righ

0.91

 LEFT

0.91

right

0.88

右

0.88

 Right

0.87

 Left

0.86

 right

0.84

RIGHT

0.84

Activations Density 0.206%

references to left and right in a spatial or directional context

No Comments

No Known Activations