INDEX

Explanations

phrases indicating a large quantity or abundance of items or concepts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 11-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_11/width_16k/average_l0_80

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.11.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

CrossRef

-0.91

setVerticalGroup

-0.81

 invokingState

-0.73

/*---

-0.73

 Schäfer

-0.72

CardHeader

-0.72

Suz

-0.71

δες

-0.71

 suicidal

-0.71

 Schaefer

-0.71

POSITIVE LOGITS

lot

1.62

 lots

1.41

 alot

1.32

 LOTS

1.27

Lot

1.27

Lots

1.26

 Lots

1.24

Lot

1.23

LOT

1.20

lots

1.00

Activations Density 0.044%

phrases indicating a large quantity or abundance of items or concepts

No Comments

No Known Activations