INDEX

Explanations

emotionally reflective language related to personal experiences and desires

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 19-gemmascope-mlp-16k

Configuration

google/gemma-scope-2b-pt-mlp/layer_19/width_16k/average_l0_109

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.19.hook_mlp_out

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

AndEndTag

-0.76

usschuss

-0.59

invokeLater

-0.58

ocity

-0.57

XMLSchema

-0.57

MathML

-0.56

 שוליים

-0.56

Discipline

-0.55

httphttps

-0.55

 Discipline

-0.55

POSITIVE LOGITS

 الحره

0.47

ziasztok

0.46

IVEREF

0.46

 konuş

0.45

 دیکھیے

0.45

مشاه

0.42

publicain

0.42

 شهری

0.42

asem

0.42

 kasarigan

0.42

Activations Density 0.192%

emotionally reflective language related to personal experiences and desires

No Comments

No Known Activations