INDEX

Explanations

references to illness or medical conditions

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

google/gemma-scope-2b-pt-res/layer_2/width_16k/average_l0_141

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.2.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

 BoxDecoration

-0.61

nery

-0.56

κε

-0.56

盆

-0.56

 talk

-0.54

 roto

-0.51

imeter

-0.51

tem

-0.50

tó

-0.50

mentaux

-0.50

POSITIVE LOGITS

ill

1.13

lbl

0.93

lbl

0.83

Ill

0.81

Ill

0.80

__":

0.77

 विश्वसनीयता

0.71

Cant

0.70

 Nutella

0.69

__":

0.69

Activations Density 0.019%

references to illness or medical conditions

No Comments

No Known Activations