INDEX

Explanations

no specific significant activations, indicating it does not detect any particular feature or information in the given document

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 13-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_13/width_16k/average_l0_84

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.13.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

<eos>

-0.69

“

-0.63

 that

-0.61

new

-0.60

and

-0.60

 this

-0.58

 make

-0.57

big

-0.56

 full

-0.56

tõ

-0.55

POSITIVE LOGITS

AnimationsModule

0.75

EndProject

0.67

 Himo

0.66

</caption>

0.65

piram

0.65

InstrumentedTest

0.64

 disambiguazione

0.64

IsMutable

0.63

SourceChecksum

0.62

 Chwiliwch

0.62

Activations Density 0.170%

no specific significant activations, indicating it does not detect any particular feature or information in the given document

No Comments

No Known Activations