INDEX

Explanations

references to "real" in various contexts, particularly related to time and data

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B @ 38-gemmascope-res-16k

Configuration

google/gemma-scope-9b-pt-res/layer_38/width_16k/average_l0_128

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.38.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

 Wikimedijinoj

-0.54

 kaarangay

-0.47

SharedDtor

-0.46

TagMode

-0.45

 really

-0.45

reid

-0.44

PreferredItem

-0.43

aarrggbb

-0.43

antMatchers

-0.42

DockStyle

-0.42

POSITIVE LOGITS

 estate

0.94

estate

0.76

ignment

0.75

 Estate

0.69

izable

0.69

politik

0.69

 ESTATE

0.66

location

0.66

igned

0.65

locating

0.65

Activations Density 0.141%

references to "real" in various contexts, particularly related to time and data

No Comments

No Known Activations