INDEX

Explanations

instances of characters showing emotional responses and interactions

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

Characters responding or reacting

np_acts-logits-general · gemini-2.0-flash

responses and reactions

np_acts-logits-general · gemini-2.5-flash-lite

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.16.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

 >=",

-0.79

UnknownFields

-0.70

تقاوى

-0.70

PMailer

-0.67

oredCriteria

-0.63

Rhestr

-0.61

KURZBESCHREIBUNG

-0.58

UVWXYZ

-0.56

 CreateTagHelper

-0.56

ngdoc

-0.55

POSITIVE LOGITS

 reply

0.59

 replied

0.56

 nodded

0.56

 responded

0.54

 laughed

0.51

 replies

0.49

 response

0.49

 countered

0.48

 retort

0.48

那是

0.48

Activations Density 0.073%

instances of characters showing emotional responses and interactions

Characters responding or reacting

responses and reactions

No Comments

No Known Activations