INDEX

Explanations

references to future events or actions

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

WriteBarrier

-0.79

EndContext

-0.75

/**

-0.71

principalColumn

-0.67

 useDispatch

-0.66

WillAppear

-0.65

serviceWorker

-0.65

Revenir

-0.61

ymce

-0.59

XmlAccessorType

-0.58

POSITIVE LOGITS

later

1.20

 later

1.19

 late

1.06

Later

1.04

 LATER

0.97

 Later

0.95

 earlier

0.87

 senare

0.82

 pozdě

0.81

 Late

0.79

Activations Density 0.153%

references to future events or actions

No Comments

No Known Activations