INDEX

Explanations

negative descriptions and complaints related to experiences

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-65k

Configuration

google/gemma-scope-2b-pt-res/layer_12/width_65k/average_l0_72

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

65,536

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

RenderAtEndOf

-0.69

imanapun

-0.63

midler

-0.60

 recargable

-0.57

KommentareTeilen

-0.56

 lèvres

-0.55

 rêves

-0.54

HasAnnotation

-0.54

bkz

-0.54

lamabad

-0.54

POSITIVE LOGITS

شهاد

0.64

 ProtoMessage

0.52

 StatefulWidget

0.51

Izvori

0.49

 onCancelled

0.48

rzost

0.46

 محفوظة

0.46

centage

0.46

foria

0.46

 rushed

0.45

Activations Density 0.088%

negative descriptions and complaints related to experiences

No Comments

No Known Activations