INDEX

Explanations

references to academic topics or academic-related terms

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.12.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

nif

-0.75

Sirius

-0.72

underline

-0.71

ses

-0.71

 Sirius

-0.70

 Dogs

-0.69

gib

-0.68

toPromise

-0.67

 dogs

-0.67

gib

-0.67

POSITIVE LOGITS

Academics

1.21

Aca

1.19

Aca

1.14

 academics

1.03

 ―――――

1.02

 acadé

1.02

 academies

1.01

 academy

1.00

 académico

0.99

 Acad

0.97

Activations Density 0.084%

references to academic topics or academic-related terms

No Comments

No Known Activations