INDEX

Explanations

proper nouns, including names and places

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

PreferredItem

-0.94

Personensuche

-0.92

ValueStyle

-0.89

 BIBSYS

-0.88

:✨

-0.80

ieteur

-0.79

 ويكيپيديا

-0.77

 Familienname

-0.75

 absl

-0.74

Примітки

-0.74

POSITIVE LOGITS

 Monti

0.88

 Janis

0.81

 Honig

0.75

Kon

0.72

 Richt

0.71

 Camb

0.70

Кон

0.69

Kon

0.68

()].

0.68

Camb

0.67

Activations Density 2.745%

proper nouns, including names and places

No Comments

No Known Activations