INDEX

Explanations

references to folders and plugins in a technical context

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 0-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_0/width_16k/average_l0_105

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.0.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

er

-0.60

dem

-0.54

los

-0.52

tia

-0.51

far

-0.49

ItemBackground

-0.49

det

-0.49

el

-0.48

burgo

-0.48

POSITIVE LOGITS

Efq

1.08

__':

1.00

 itſelf

0.99

__":

0.97

 reaſon

0.94

 myſelf

0.94

 cauſe

0.94

 himſelf

0.92

 fevere

0.91

 ſche

0.91

Activations Density 0.205%

references to folders and plugins in a technical context

No Comments

No Known Activations