INDEX

Explanations

terms related to operations or actions in code or programming

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.21.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

 <=",

-0.73

 Roskov

-0.69

исленность

-0.64

DebuggerStep

-0.63

 Hathaway

-0.61

})`

-0.59

IContainer

-0.58

RTEE

-0.56

 GenerationType

-0.56

 CHAPITRE

-0.56

POSITIVE LOGITS

*{

0.52

enschappelijke

0.49

<strong>

0.49

hani

0.45

zku

0.44

MENAFN

0.44

jenigen

0.44

 ajuta

0.44

InstrumentedTest

0.44

appliquer

0.43

Activations Density 0.020%

terms related to operations or actions in code or programming

No Comments

No Known Activations