INDEX

Explanations

references to alignment and orientation in various contexts

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

 contextLoads

-0.59

eradish

-0.55

gın

-0.55

 refuted

-0.54

TNI

-0.53

قایناقلار

-0.52

}-${

-0.51

olo

-0.51

 maler

-0.50

hammer

-0.50

POSITIVE LOGITS

 align

0.97

 orientation

0.94

CloseOperation

0.91

 orient

0.86

 alignment

0.86

orientation

0.84

 Orientation

0.84

orient

0.81

UnusedPrivate

0.79

 orientations

0.79

Activations Density 0.127%

references to alignment and orientation in various contexts

No Comments

No Known Activations