INDEX

Explanations

phrases that indicate conditional or definitional contexts, commonly seen in mathematical or formal descriptions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.5.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

ivez

-0.47

Aiheesta

-0.47

Clik

-0.44

 pomy

-0.43

Pull

-0.42

 towards

-0.42

 Richtung

-0.42

 onData

-0.41

sog

-0.41

 stocks

-0.41

POSITIVE LOGITS

setVerticalGroup

1.01

PerformLayout

0.85

URLException

0.85

 HasFactory

0.81

AndEndTag

0.80

principalColumn

0.78

 StatelessWidget

0.77

 Privacidade

0.76

 surla

0.76

 InputDecoration

0.76

Activations Density 0.402%

phrases that indicate conditional or definitional contexts, commonly seen in mathematical or formal descriptions

No Comments

No Known Activations