INDEX

Explanations

terms related to geographical directions and locations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 0-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_0/width_16k/average_l0_105

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.0.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

UserScript

-0.86

Dữ

-0.81

 Савезне

-0.79

endphp

-0.76

Datuak

-0.74

IUrlHelper

-0.71

UnsafeEnabled

-0.70

 <<<<<<<<<<<<<<

-0.70

psies

-0.70

GraphicsUnit

-0.70

POSITIVE LOGITS

 western

0.73

Ne

0.72

 northern

0.71

ne

0.68

 southern

0.68

 west

0.67

 eastern

0.66

neo

0.61

west

0.61

 northerly

0.61

Activations Density 0.139%

terms related to geographical directions and locations

No Comments

No Known Activations