INDEX

Explanations

references to specific data types or programming constructs

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

Personendaten

-1.12

 '\\;'

-1.05

 nahilalakip

-1.00

 otomatig

-0.99

 CreateTagHelper

-0.95

 kaarangay

-0.88

GEBURTSDATUM

-0.85

WebVitals

-0.85

AndroidJUnit

-0.80

principalColumn

-0.75

POSITIVE LOGITS

npos

0.54

Ve

0.49

Ve

0.49

[^

0.47

برى

0.44

[/

0.44

unes

0.43

::$

0.43

sic

0.43

หม

0.42

Activations Density 0.393%

references to specific data types or programming constructs

No Comments

No Known Activations