INDEX

Explanations

terms related to navigation and spatial orientation

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.3.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

ValueStyle

-1.06

########.

-1.05

:+:

-0.84

 &___

-0.78

uxxxx

-0.75

+#+

-0.75

 Xunit

-0.74

ьаж

-0.74

mushroom

-0.70

Conan

-0.70

POSITIVE LOGITS

 navigation

2.96

 Navigation

2.73

 navig

2.71

 navigate

2.57

 Navig

2.53

Navigation

2.45

navigation

2.42

navig

2.41

Navig

2.40

 navigating

2.37

Activations Density 0.060%

terms related to navigation and spatial orientation

No Comments

No Known Activations