INDEX

Explanations

spatial positioning and direction terms in code or layout specifications

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 4-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_4/width_16k/average_l0_124

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.4.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

wiście

-0.65

 contado

-0.60

makeText

-0.56

Noun

-0.54

NetworkInfo

-0.54

σ

-0.53

 made

-0.53

vician

-0.53

DidLoad

-0.53

 tố

-0.51

POSITIVE LOGITS

right

1.10

Right

1.08

RIGHT

1.08

getRight

1.02

 Right

1.00

setRight

0.97

 RIGHT

0.93

 houſe

0.86

 Droit

0.86

 myſelf

0.83

Activations Density 0.170%

spatial positioning and direction terms in code or layout specifications

No Comments

No Known Activations