INDEX

Explanations

phrases that suggest consideration or awareness

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

google/gemma-scope-2b-pt-res/layer_2/width_16k/average_l0_141

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.2.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

glTex

-0.55

("")]

-0.52

 setId

-0.52

berglass

-0.51

 chaired

-0.48

chom

-0.47

americano

-0.47

kip

-0.47

 monoton

-0.47

ammer

-0.47

POSITIVE LOGITS

 تضيفلها

0.79

EndContext

0.73

 NSCoder

0.72

PerformLayout

0.71

SuccessListener

0.69

apimachinery

0.67

 confronti

0.64

URLException

0.64

 sanitarias

0.63

 mind

0.62

Activations Density 0.134%

phrases that suggest consideration or awareness

No Comments

No Known Activations