INDEX

Explanations

references to scientific methodologies and technical details

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

stretchr

-0.50

 NDEBUG

-0.47

initWithFrame

-0.44

 gewesen

-0.43

AxisAlignment

-0.42

そんな

-0.40

ister

-0.40

IGO

-0.40

tská

-0.39

setArguments

-0.39

POSITIVE LOGITS

RegressionTest

1.07

parsedMessage

0.92

 iprot

0.88

 betweenstory

0.82

ViewFeatures

0.78

 linkovi

0.78

]){

0.73

ⓧ

0.73

 Roskov

0.73

])).

0.73

Activations Density 2.365%

references to scientific methodologies and technical details

No Comments

No Known Activations