INDEX

Explanations

phrases that express disbelief or the need for validation of information

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.12.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

LookAnd

-0.99

 CreateTagHelper

-0.91

VYMaps

-0.73

 مشين

-0.73

OGND

-0.72

"}")

-0.71

ukunft

-0.69

DockStyle

-0.69

IntoConstraints

-0.67

$_"

-0.62

POSITIVE LOGITS

balleur

0.54

0.50

Nonetheless

0.48

Laughs

0.47

 ExecuteAsync

0.46

 Nonetheless

0.46

—

0.46

grained

0.46

 insiste

0.45

 kasarigan

0.45

Activations Density 0.076%

phrases that express disbelief or the need for validation of information

No Comments

No Known Activations