INDEX

Explanations

phrases centered around personal identity or self-reference

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B @ 31-gemmascope-res-16k

Configuration

google/gemma-scope-9b-pt-res/layer_31/width_16k/average_l0_114

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.31.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

 autorytatywna

-0.59

DockStyle

-0.45

 ControllerBase

-0.45

TextHelper

-0.43

Билгалдахарш

-0.41

 ReactDOM

-0.40

_",

-0.40

nloa

-0.39

TagNumber

-0.39

}*/

-0.39

POSITIVE LOGITS

 guess

0.59

 digo

0.51

am

0.50

 myself

0.48

 admit

0.48

Tracce

0.48

 hope

0.48

 believe

0.47

 Admit

0.47

 however

0.47

Activations Density 0.179%

phrases centered around personal identity or self-reference

No Comments

No Known Activations