INDEX

Explanations

expressions related to awareness and realization

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

={({

-0.54

fiz

-0.52

 Etrus

-0.51

hape

-0.50

 sqlSession

-0.50

ContentAsync

-0.49

 noix

-0.49

ษา

-0.49

inephrine

-0.49

mmons

-0.49

POSITIVE LOGITS

 AssemblyCulture

0.86

AndEndTag

0.78

IntoConstraints

0.77

 unaware

0.71

فایل‌لار

0.69

 ويكيپيديا

0.64

 unnoticed

0.64

 vPvB

0.63

GEBURTSDATUM

0.61

 HasFactory

0.61

Activations Density 0.253%

expressions related to awareness and realization

No Comments

No Known Activations