INDEX

Explanations

names of individuals and their roles in a conversational context

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

Following "talk" or "<start_of_turn>user"

np_acts-logits-general · gemini-2.0-flash

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

google/gemma-scope-9b-it-res/layer_31/width_16k/average_l0_76

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

tagHelperRunner

-0.50

一応

-0.47

 JpaRepository

-0.46

 >=",

-0.46

slika

-0.45

 ModelExpression

-0.43

 hjemmeside

-0.42

 Normdatei

-0.42

 vermeld

-0.41

 specified

-0.41

POSITIVE LOGITS

 guest

0.80

guest

0.73

Exclusive

0.69

exclu

0.69

 exclusive

0.69

 joins

0.69

Guest

0.68

exclusive

0.68

今回は

0.66

 exklu

0.66

Activations Density 0.162%

names of individuals and their roles in a conversational context

Following "talk" or "<start_of_turn>user"

No Comments

No Known Activations