INDEX

Explanations

references to names or terms associated with specific meanings or definitions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.12.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

 Houſe

-0.61

 myſelf

-0.56

 Conſ

-0.55

 houſe

-0.51

 Majefty

-0.50

 missed

-0.49

 Diſ

-0.49

 خط

-0.49

 tslint

-0.49

 miſ

-0.47

POSITIVE LOGITS

 lenker

0.66

MLLoader

0.64

 claros

0.60

 censo

0.57

 Sanskrit

0.57

 donnés

0.57

UnsafeEnabled

0.56

 kurios

0.56

 détru

0.56

ícios

0.56

Activations Density 0.110%

references to names or terms associated with specific meanings or definitions

No Comments

No Known Activations