INDEX

Explanations

questions and requests for clarification or explanation

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

Efq

-1.02

 myſelf

-0.97

 Theſe

-0.96

 photolibrary

-0.95

 وتسجيلات

-0.95

 whoſe

-0.95

 Reſ

-0.94

 Houſe

-0.94

 Monfieur

-0.94

 leaſt

-0.93

POSITIVE LOGITS

 суть

0.61

0.55

0.54

0.50

 Specifically

0.49

具体

0.49

如下

0.47

 Hintergrund

0.47

 polega

0.47

Activations Density 0.481%

questions and requests for clarification or explanation

No Comments

No Known Activations