INDEX

Explanations

mentions of "latest" or "latest developments."

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 10-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_10/width_16k/average_l0_77

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.10.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

aarrggbb

-0.75

kheim

-0.72

RMS

-0.66

cdk

-0.66

к

-0.65

stanford

-0.65

 Rockford

-0.63

ienda

-0.62

Kalb

-0.61

sog

-0.61

POSITIVE LOGITS

 LATEST

1.48

 latest

1.39

Latest

1.33

latest

1.32

 Latest

1.30

LATEST

1.24

 newest

1.09

 最新

1.00

 neuesten

0.97

newest

0.94

Activations Density 0.042%

mentions of "latest" or "latest developments."

No Comments

No Known Activations