INDEX

Explanations

phrases related to formal 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 @ 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

expandindo

-0.68

RectangleBorder

-0.55

 utafitiHapana

-0.54

 виправивши

-0.54

indd

-0.47

enumii

-0.47

ὐ

-0.45

DockStyle

-0.45

 insuffisamment

-0.45

そのような

-0.44

POSITIVE LOGITS

Diwedd

0.83

 nakalista

0.81

يميديا

0.77

yntaxException

0.75

CPtr

0.69

 kasarigan

0.68

ConstraintMaker

0.68

 resourceCulture

0.64

pherals

0.63

 verwijzen

0.63

Activations Density 1.073%

phrases related to formal assessments or evaluations

No Comments

No Known Activations