INDEX

Explanations

phrases indicating the presence of health-related challenges or issues in a specific context

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.16.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

 تضيفلها

-0.75

AddTagHelper

-0.65

__(/*!

-0.62

UnusedPrivate

-0.61

imageshack

-0.58

guenos

-0.57

BeginContext

-0.56

awtextra

-0.56

 ProtoMessage

-0.54

andExpect

-0.53

POSITIVE LOGITS

 cuanto

0.65

 determining

0.62

AutoresizingMask

0.59

 OMIT

0.56

 regards

0.55

braio

0.55

 matters

0.54

otu

0.54

 regard

0.53

 Kecil

0.52

Activations Density 0.321%

phrases indicating the presence of health-related challenges or issues in a specific context

No Comments

No Known Activations