INDEX

Explanations

expressions of honesty and self-awareness in discourse

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

MigrationBuilder

-0.85

-0.63

 <>",

-0.63

 FormsModule

-0.63

mybatisplus

-0.63

 KeyError

-0.63

 captioned

-0.62

ADI

-0.62

 saites

-0.61

 disponibilités

-0.61

POSITIVE LOGITS

0.54

0.51

the

0.49

 hogy

0.49

 this

0.49

0.47

gar

0.46

 stay

0.46

Activations Density 0.320%

expressions of honesty and self-awareness in discourse

No Comments

No Known Activations