INDEX

Explanations

spatial positioning and layout-related terms

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.12.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

CodeAttribute

-0.54

 entière

-0.51

demik

-0.51

 elég

-0.49

amp

-0.47

็ง

-0.47

 rajut

-0.46

CHANGE

-0.45

 soldati

-0.45

ENDPOINT

-0.44

POSITIVE LOGITS

PreferredItem

0.80

رشف

0.79

AutoScaleMode

0.79

bootstrapcdn

0.77

 ExecuteAsync

0.77

存于互联网档案馆

0.74

 ComVisible

0.74

icitis

0.71

ClientSize

0.70

IntoConstraints

0.69

Activations Density 0.141%

spatial positioning and layout-related terms

No Comments

No Known Activations