INDEX

Explanations

phrases that indicate exactness or accuracy

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B @ 0-gemmascope-res-16k

Configuration

google/gemma-scope-9b-pt-res/layer_0/width_16k/average_l0_129

Prompts (Dashboard)

24,576 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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

Kep

-0.48

 input

-0.38

Gad

-0.38

 machinery

-0.38

categor

-0.38

 stating

-0.37

 States

-0.37

הערות

-0.36

IN

-0.36

st

-0.36

POSITIVE LOGITS

Precise

0.79

 Precise

0.76

precise

0.74

 precisely

0.70

#+#

0.70

Exactly

0.65

 zijne

0.65

Snow

0.65

 ainfi

0.65

exactly

0.64

Activations Density 0.373%

phrases that indicate exactness or accuracy

No Comments

No Known Activations