INDEX

Explanations

phrases that refer to taking a look or examining something

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

apimachinery

-0.62

toms

-0.61

 păr

-0.56

ेशा

-0.55

 agricoles

-0.53

 längre

-0.53

 slå

-0.51

DET

-0.51

 skriva

-0.50

 Kette

-0.49

POSITIVE LOGITS

сылкі

0.84

 CURIAM

0.84

 glance

0.81

reportWebVitals

0.81

 ProtoMessage

0.78

 glances

0.77

 peek

0.76

 vistazo

0.74

 nakalista

0.72

ceptives

0.72

Activations Density 0.168%

phrases that refer to taking a look or examining something

No Comments

No Known Activations