INDEX

Explanations

instances of the word "Created" and related actions indicating creation or data handling

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

featureID

-1.24

ArgsConstructor

-1.17

 myſelf

-0.87

TypedDataSet

-0.87

 magasiner

-0.78

 ProtoMessage

-0.77

 itſelf

-0.76

LookAnd

-0.74

afficheront

-0.74

 Esprit

-0.74

POSITIVE LOGITS

TagHelpers

1.61

BuildContext

0.92

fasterxml

0.91

SuppressMessage

0.86

 EdgeInsets

0.80

PathVariable

0.79

cdn

0.71

jspx

0.69

ForeignKey

0.66

cline

0.66

Activations Density 0.011%

instances of the word "Created" and related actions indicating creation or data handling

No Comments

No Known Activations