INDEX

Explanations

quantifiable details and numerical data in various contexts

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

 both

-0.53

Both

-0.50

 Both

-0.47

Ambos

-0.46

BOTH

-0.45

two

-0.43

бир

-0.42

Two

-0.42

both

-0.42

 Beide

-0.42

POSITIVE LOGITS

 Roskov

1.00

ArrowToggle

0.95

PerformLayout

0.95

 समीक्षक

0.88

 Савезне

0.85

 autorytatywna

0.84

ValueStyle

0.84

)");

0.82

RegressionTest

0.82

 <>",

0.81

Activations Density 0.816%

quantifiable details and numerical data in various contexts

No Comments

No Known Activations