INDEX

Explanations

multi-line mathematical expressions formatted in alignment

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 25-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_25/width_16k/average_l0_116

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.25.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

 betweenstory

-0.65

WritableDatabase

-0.63

 Below

-0.62

Below

-0.60

 Above

-0.60

ValueStyle

-0.57

Above

-0.55

 below

-0.53

GEBURTSDATUM

-0.52

Hochspringen

-0.52

POSITIVE LOGITS

IntoConstraints

0.53

новништво

0.52

 étoient

0.48

 droits

0.46

@"

0.45

 getItemId

0.45

windowFixed

0.44

 étranger

0.44

Camp

0.44

zzá

0.44

Activations Density 0.154%

multi-line mathematical expressions formatted in alignment

No Comments

No Known Activations