INDEX

Explanations

references to specific scientific or technical terms related to processes or functions

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

starting with "par" (or "Par")

np_acts-logits-general · gemini-2.0-flash

words starting with par

np_acts-logits-general · gemini-2.5-flash-lite

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.16.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

SpringBootTest

-0.92

>"+

-0.75

时候

-0.74

DOCTYPE

-0.74

>");

-0.74

 Roskov

-0.74

")){

-0.72

ImageContext

-0.72

/"+

-0.72

Sucesor

-0.72

POSITIVE LOGITS

PAR

1.18

PAR

1.10

 Parke

1.08

par

1.07

Pars

1.05

 pars

1.02

 Paro

1.00

 Parr

0.98

 Parrish

0.97

 parks

0.96

Activations Density 0.127%

references to specific scientific or technical terms related to processes or functions

starting with "par" (or "Par")

words starting with par

No Comments

No Known Activations