INDEX

Explanations

bullet points or list indicators in the text

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

zwe

-0.82

innig

-0.80

 المعيارى

-0.77

OfBirth

-0.75

 SwitchCompat

-0.75

 Jacob

-0.74

ksjon

-0.74

 Luch

-0.74

 Garg

-0.73

qos

-0.73

POSITIVE LOGITS

••

1.48

.•

1.46

°•

1.31

•••

1.31

••••

1.28

•

1.26

~•

1.16

er

1.16

)•

1.07

 ••

1.01

Activations Density 0.042%

bullet points or list indicators in the text

No Comments

No Known Activations