INDEX

Explanations

statements and phrases about personal identity and moral integrity

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.20.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

ंदीखरीदारी

-0.69

 desiring

-0.61

 defire

-0.60

 hoping

-0.59

 awaiting

-0.59

deserved

-0.57

Hoping

-0.56

HORE

-0.56

 attempting

-0.56

 eager

-0.56

POSITIVE LOGITS

 LUMP

0.71

pyplot

0.62

kuuta

0.56

 kreatif

0.53

 part

0.51

 creative

0.50

 đó

0.50

 ולה

0.50

WriteAttribute

0.48

 paziente

0.48

Activations Density 0.151%

statements and phrases about personal identity and moral integrity

No Comments

No Known Activations