INDEX

Explanations

instructions related to navigating a user interface or website

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 13-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_13/width_16k/average_l0_84

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.13.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

 Meksiku

-0.76

 ModelExpression

-0.66

InputTagHelper

-0.63

delà

-0.59

StructEnd

-0.55

-0.54

ArrowToggle

-0.54

addCriterion

-0.53

المشاركات

-0.53

ApiModel

-0.52

POSITIVE LOGITS

 Wikimedijinoj

0.58

 juſ

0.56

 column

0.56

amentals

0.55

varande

0.53

 corner

0.52

 popup

0.51

neſs

0.51

 bottom

0.51

 Decke

0.50

Activations Density 0.185%

instructions related to navigating a user interface or website

No Comments

No Known Activations