INDEX

Explanations

terms related to statistical analysis and experimental results

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

pyplot

-0.47

 aquilo

-0.46

InstrumentedTest

-0.45

hexane

-0.43

tér

-0.42

 dear

-0.41

რ

-0.40

 everything

-0.40

HSA

-0.40

 ISBN

-0.39

POSITIVE LOGITS

ItemBackground

0.73

ⓧ

0.69

ftagPool

0.69

migrationBuilder

0.68

Geplaatst

0.67

OGND

0.67

ThroughAttribute

0.66

sizeCache

0.65

=$?

0.64

 AttributeSet

0.64

Activations Density 4.033%

terms related to statistical analysis and experimental results

No Comments

No Known Activations