INDEX

Explanations

phrases related to personal narratives and experiences

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 4-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_4/width_16k/average_l0_124

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.4.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

+#+#

-0.56

 виправивши

-0.52

rungsseite

-0.50

 jPanel

-0.48

Cubit

-0.48

sie

-0.47

पया

-0.47

ings

-0.47

IBinder

-0.47

Referințe

-0.46

POSITIVE LOGITS

AndEndTag

0.75

 Schiffe

0.65

éroport

0.64

 myſelf

0.63

 himſelf

0.62

łbym

0.62

 alſo

0.61

 purpoſe

0.61

korb

0.61

 linkovi

0.60

Activations Density 2.066%

phrases related to personal narratives and experiences

No Comments

No Known Activations