INDEX

Explanations

technical terms and acronyms related to data transmission and communication protocols

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

 Milner

-0.81

 myſelf

-0.81

 Cowan

-0.77

 becauſe

-0.76

Efq

-0.75

coz

-0.75

 poffible

-0.74

 faſt

-0.72

UPI

-0.71

();*/

-0.71

POSITIVE LOGITS

CH

1.01

CH

1.00

 Lach

0.91

MCH

0.90

Gh

0.87

fh

0.86

Lach

0.86

 Chávez

0.84

Uch

0.84

ZH

0.84

Activations Density 2.659%

technical terms and acronyms related to data transmission and communication protocols

No Comments

No Known Activations