INDEX

Explanations

method calls related to setting and updating values in programming contexts

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

Code related to setting values or states

np_acts-logits-general · gemini-2.0-flash

setting methods

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B @ 28-gemmascope-res-16k

Configuration

google/gemma-scope-9b-pt-res/layer_28/width_16k/average_l0_119

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.28.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

RegressionTest

-0.77

parsedMessage

-0.57

SequentialGroup

-0.53

ISupport

-0.52

richTextPanel

-0.52

évaluateur

-0.49

 onOptions

-0.49

 препратки

-0.49

exitRule

-0.48

tagHelperRunner

-0.48

POSITIVE LOGITS

เป็น

0.36

 AssemblyTitle

0.36

set

0.35

 focus

0.33

 Camb

0.33

setVerticalGroup

0.32

 healthier

0.31

dė

0.31

ให้

0.31

 derivative

0.30

Activations Density 0.159%

method calls related to setting and updating values in programming contexts

Code related to setting values or states

setting methods

No Comments

No Known Activations

method calls related to setting and updating values in programming contexts

Code related to setting values or states

setting methods

No Comments

No Known Activations