INDEX

Explanations

instances of the word "created" and its variations, typically in a context related to authorship or documentation

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

lapsible

-0.71

issauga

-0.68

 socios

-0.66

assertThrows

-0.65

chige

-0.65

commentId

-0.64

liese

-0.64

 Antalya

-0.64

accumulative

-0.64

verwijspagina

-0.63

POSITIVE LOGITS

created

1.33

 Created

1.29

Created

1.28

 CREATED

1.21

 created

1.19

Creator

1.16

CREATED

1.12

 Creator

1.06

creator

1.05

Creation

1.02

Activations Density 0.077%

instances of the word "created" and its variations, typically in a context related to authorship or documentation

No Comments

No Known Activations