INDEX

Explanations

phrases indicating direction or movement towards a goal or endpoint

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 10-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_10/width_16k/average_l0_77

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.10.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

 Calvo

-0.84

 foglal

-0.72

 fatica

-0.68

 poffe

-0.67

물

-0.67

-0.65

 Bede

-0.63

ыре

-0.62

 riuscito

-0.62

POSITIVE LOGITS

toward

1.81

towards

1.77

 Towards

1.75

 Toward

1.75

 toward

1.74

Towards

1.68

 towards

1.63

Toward

1.61

 hacia

1.25

 envers

1.19

Activations Density 0.060%

phrases indicating direction or movement towards a goal or endpoint

No Comments

No Known Activations