INDEX

Explanations

phrases that indicate significant impacts or roles in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B @ 33-gemmascope-res-16k

Configuration

google/gemma-scope-9b-pt-res/layer_33/width_16k/average_l0_114

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.33.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

aktery

-0.42

ติด

-0.38

 Reactor

-0.37

Typical

-0.37

 Typical

-0.35

Needs

-0.35

 Applies

-0.34

</>

-0.34

вость

-0.34

 Akti

-0.33

POSITIVE LOGITS

 bearing

0.66

tvguidetime

0.60

 positive

0.58

TypedDataSet

0.55

bearing

0.55

 profound

0.55

 indirect

0.54

 immeasurable

0.54

 significant

0.53

RenderAtEndOf

0.53

Activations Density 0.301%

phrases that indicate significant impacts or roles in various contexts

No Comments

No Known Activations