INDEX

Explanations

the word "from" in various contexts, often indicating sources or origins in a document

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 23-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_23/width_16k/average_l0_75

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.23.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

 beginnetje

-0.69

 kasarigan

-0.64

Personendaten

-0.58

 autorytatywna

-0.55

WindowConstants

-0.54

WireFormat

-0.53

addContainerGap

-0.52

rungsseite

-0.51

Rhestr

-0.51

lino

-0.48

POSITIVE LOGITS

'./

1.13

"./

1.13

 '../

1.06

 "../

1.02

../

0.86

"./

0.85

 "../../

0.85

../../

0.83

'./

0.82

 '../../

0.81

Activations Density 0.018%

the word "from" in various contexts, often indicating sources or origins in a document

No Comments

No Known Activations