INDEX

Explanations

geographical locations and place names

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.5.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

usepackage

-0.68

 InputDecoration

-0.66

uronic

-0.59

ItemBackground

-0.57

pâ

-0.55

Lus

-0.55

ristas

-0.55

haustible

-0.55

 bacterio

-0.54

 Conservancy

-0.52

POSITIVE LOGITS

tvguidetime

0.87

batore

0.67

رشف

0.67

 NSCoder

0.66

 للاسماء

0.65



0.60

 ویکی‌پدیای

0.58

 Amarillo

0.57

\{\\

0.57

лябин

0.54

Activations Density 0.483%

geographical locations and place names

No Comments

No Known Activations