INDEX

Explanations

instances of the word "interesting."

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 1-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_1/width_16k/average_l0_102

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.1.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

 كومونز

-0.92

 مصرى

-0.73

__':

-0.72

mahami

-0.68

ArgsConstructor

-0.66

CloseOperation

-0.65

principalColumn

-0.64

 manchmal

-0.64

__':

-0.64

 AssemblyProduct

-0.64

POSITIVE LOGITS

 interesting

0.90

interesting

0.81

 Interesting

0.73

 regarding

0.68

Interesting

0.65

Dir

0.61

 interessante

0.59

dir

0.57

regarding

0.57

 interess

0.57

Activations Density 0.078%

instances of the word "interesting."

No Comments

No Known Activations