INDEX

Explanations

statements about state changes, condition assessments, or evaluations

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

 getItemCount

-0.57

UpInside

-0.54

 Monfieur

-0.53

 ſeveral

-0.53

DebuggerNonUser

-0.52

ছ

-0.51

ülő

-0.49

 greifen

-0.48

говари

-0.48

 Morgan

-0.48

POSITIVE LOGITS

 فريبيس

0.93

 gynhyrchwyd

0.67

 חיצוניים

0.67

DJANGO

0.66

RectangleBorder

0.65

ImageContext

0.65

GEBURTSDATUM

0.64

 հղումներ

0.63

MethodManager

0.63

 للمعارف

0.61

Activations Density 0.733%

statements about state changes, condition assessments, or evaluations

No Comments

No Known Activations