INDEX

Explanations

patterns of structured data, likely related to formatted tables or datasets in scientific contexts

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-65k

Configuration

google/gemma-scope-2b-pt-res/layer_12/width_65k/average_l0_72

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

65,536

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

+#+#

-0.63

 veckor

-0.59

}{*}{

-0.59

 песен

-0.58

 AsyncTask

-0.56

 pedimos

-0.56

 Overton

-0.54

::_('

-0.54

 jspb

-0.54

 लेकर

-0.54

POSITIVE LOGITS

1.03

ształ

0.85

 nahilalakip

0.78

Spoljašnje

0.76

vanni

0.76

 autorytatywna

0.72

AppCompat

0.67

 Schlegel

0.66

Activations Density 0.357%

patterns of structured data, likely related to formatted tables or datasets in scientific contexts

No Comments

No Known Activations