INDEX

Explanations

terms associated with honor and integrity

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

terms related to honor and commendable actions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 7-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_7/width_16k/average_l0_69

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.7.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

<blockquote>

-0.74

etCode

-0.68

 initComponents

-0.65

digm

-0.64

 bang

-0.64

 levi

-0.61

تين

-0.60

ympto

-0.58

kegaard

-0.58

 Goliath

-0.58

POSITIVE LOGITS

 HONOR

1.97

 honor

1.93

 honors

1.85

honor

1.83

 honour

1.80

 Honor

1.79

Honor

1.74

 honored

1.72

hon

1.69

 onor

1.67

Activations Density 0.049%

terms associated with honor and integrity

terms related to honor and commendable actions

No Comments

No Known Activations