INDEX

Explanations

references to data input and output operations in the context of programming

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.5.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

UnusedPrivate

-0.52

reactstrap

-0.52

LookAnd

-0.52

RUnlock

-0.51

 ModelExpression

-0.51

escalier

-0.49

getTransaction

-0.48

SpringRunner

-0.47

 ngang

-0.46

DateTimeField

-0.46

POSITIVE LOGITS

INTO

0.77

Kjelder

0.73

 صوتيه

0.73

 INTO

0.72

 onto

0.71

 kwenye

0.67

ostream

0.67

addTo

0.66

 cikin

0.65

 破解

0.65

Activations Density 0.541%

references to data input and output operations in the context of programming

No Comments

No Known Activations