INDEX

Explanations

narratives involving manipulation and conflict among characters

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 25-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_25/width_16k/average_l0_116

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.25.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

 समीक्षाओं

-0.58

 Indian

-0.57

 CreateTagHelper

-0.56

 Andhra

-0.54

первых

-0.53

<?

-0.53

Indian

-0.53

évaluateur

-0.51

 Tamil

-0.51

 Essentially

-0.50

POSITIVE LOGITS

 мәкал

0.60

Da

0.55

 Vans

0.55

stonia

0.54

 misunder

0.53

 Servant

0.53

ANSION

0.52

 biji

0.52

 inspector

0.51

 Bebe

0.51

Activations Density 0.051%

narratives involving manipulation and conflict among characters

No Comments

No Known Activations