INDEX

Explanations

references to corruption

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 0-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_0/width_16k/average_l0_105

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.0.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

---*/

-0.60

addCriterion

-0.52

@"/

-0.51

keyDown

-0.49

NIS

-0.48

 defaultstate

-0.48

ynia

-0.47

 istore

-0.47

Il

-0.46

Kle

-0.45

POSITIVE LOGITS

enumi

1.00

 itſelf

0.78

 Corruption

0.77

 pleaſure

0.76

 pouvoit

0.76

 Anſ

0.74

 corruption

0.73

 purpoſe

0.73

 themſelves

0.71

 Theſe

0.71

Activations Density 0.124%

references to corruption

No Comments

No Known Activations