INDEX

Explanations

terms related to increasing or enhancing processes or outcomes

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 1-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_1/width_16k/average_l0_102

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.1.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

()?;

-0.61

 valueForKey

-0.55

lader

-0.53

 собою

-0.53

릅

-0.53

переди

-0.53

atalos

-0.52

ấu

-0.52

 bParam

-0.52

Климат

-0.52

POSITIVE LOGITS

 increase

3.34

 increases

3.21

increase

3.10

 Increase

3.07

 Increases

3.01

Increase

3.00

Increases

2.91

increases

2.89

 INCREASE

2.80

 increased

2.49

Activations Density 0.181%

terms related to increasing or enhancing processes or outcomes

No Comments

No Known Activations