INDEX

Explanations

instances of casual greetings and expressions of gratitude

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

New Auto-Interp

Configuration

google/gemma-scope-9b-pt-res/layer_23/width_131k/average_l0_101

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

131,072

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

erintah

-0.55

 Kartoffeln

-0.51

 zuſammen

-0.51

 ſche

-0.51

 Kelurahan

-0.50

 Gilman

-0.48

 crackers

-0.46

 indígen

-0.46

 Geſch

-0.46

 ſei

-0.46

POSITIVE LOGITS

 nakalista

0.65

AddTagHelper

0.47

verwijspagina

0.47

GOTREF

0.45

tvguidetime

0.42

 nahilalakip

0.40

SharedCtor

0.38

 reply

0.36

脚注の使い方

0.36

MigrationBuilder

0.35

Activations Density 0.012%

instances of casual greetings and expressions of gratitude

No Comments

No Known Activations