INDEX

Explanations

names of authors and researchers

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

RegressionTest

-0.89

 <<<<<<<<<<<<<<

-0.85

MessageTagHelper

-0.61

Enllaces

-0.59

expandindo

-0.58

IContainer

-0.58

ípio

-0.56

addContainerGap

-0.55

ьаж

-0.55

Kjelder

-0.54

POSITIVE LOGITS

 Normdatei

0.62

 referenties

0.52

omiast

0.52

resizingMask

0.51

lıkla

0.49

ására

0.48

HomeAsUpEnabled

0.47

 actionPerformed

0.47

resave

0.47

 considérons

0.46

Activations Density 0.280%

names of authors and researchers

No Comments

No Known Activations