INDEX

Explanations

actions and commands related to processing or manipulating data or objects

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

Verbs followed by "the" or an article

np_acts-logits-general · gemini-2.0-flash

verbs of action

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

google/gemma-scope-9b-it-res/layer_9/width_16k/average_l0_88

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.9.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

soever

-0.41

featureID

-0.41

 JsonConvert

-0.41

 pungkasnya

-0.41

 desti

-0.40

AddTagHelper

-0.40

umumkan

-0.40

didSet

-0.38

tagHelperRunner

-0.38

いいね

-0.38

POSITIVE LOGITS

IntoConstraints

0.45

AnimationsModule

0.41

脚注の使い方

0.40

XtraReports

0.40

Filmografia

0.39

 dabei

0.38

 kèm

0.35

KommentareTeilen

0.35

imageshack

0.35

 nakalista

0.35

Activations Density 0.847%

actions and commands related to processing or manipulating data or objects

Verbs followed by "the" or an article

verbs of action

No Comments

No Known Activations