INDEX

Explanations

references to mathematical symbols and variables related to scientific or technical contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 6-gemmascope-mlp-16k

Configuration

google/gemma-scope-2b-pt-mlp/layer_6/width_16k/average_l0_133

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.6.hook_mlp_out

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

تقاوى

-0.85

 HasFactory

-0.64

Izvori

-0.64

 مشين

-0.62

 وتسجيلات

-0.61

RegressionTest

-0.60

-0.59

#+#

-0.57

nesc

-0.56

-0.54

POSITIVE LOGITS

HasAnnotation

0.50

avits

0.47

INSEE

0.46

 SqlCommand

0.44

fadeIn

0.44

DMETHOD

0.43

 franchises

0.43

TOE

0.42

bat

0.42

chanted

0.42

Activations Density 0.831%

references to mathematical symbols and variables related to scientific or technical contexts

No Comments

No Known Activations