INDEX

Explanations

names of people and companies along with their locations

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

names and locations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-131k

Configuration

google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

131,072

Data Type

float32

Hook Name

blocks.20.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

сылкі

-0.63

 kasarigan

-0.60

tagHelperRunner

-0.59

Rhestr

-0.52

UrlResolution

-0.47

featureID

-0.47

expandindo

-0.47

Bakgrunnsstoff

-0.47

iettivo

-0.46

الحياه

-0.45

POSITIVE LOGITS

 purpoſe

0.39

snow

0.37

Means

0.36

argento

0.36

 Means

0.35

appartamento

0.35

 appunt

0.35

 AssemblyVersion

0.35

nikahan

0.35

outdoor

0.33

Activations Density 0.007%

names of people and companies along with their locations

names and locations

No Comments

No Known Activations