INDEX

Explanations

references to political discourse and accusations

oai_token-act-pair · gpt-4o-mini

New Auto-Interp

Configuration

chanind/gemma-2-2b-batch-topk-matryoshka-saes-w-32k-l0-40/standard/blocks.12.hook_resid_post

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

32,768

Data Type

float32

Hook Name

blocks.12.hook_resid_post

Architecture

jumprelu

Context Size

1,024

Dataset

chanind/pile-uncopyrighted-gemma-1024-abbrv-1B

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

TagMode

-0.73

neath

-0.48

SQLiteDatabase

-0.47

bootstrapcdn

-0.45

usiai

-0.45

OGND

-0.44

ClientRect

-0.44

 persua

-0.43

testng

-0.43

Cut

-0.42

POSITIVE LOGITS

dafx

0.70

 OFDb

0.69

MigrationBuilder

0.64

 cherchés

0.61

 дописавши

0.60

 发表于

0.60

StoryboardSegue

0.58

ThroughAttribute

0.57

 invokingState

0.57

encodeWith

0.56

Activations Density 0.330%

references to political discourse and accusations

No Comments

No Known Activations

references to political discourse and accusations

No Comments

No Known Activations