INDEX

Explanations

phrases indicating limitations or constraints related to context or boundaries

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 25-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_25/width_16k/average_l0_116

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.25.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

 arrivée

-0.59

անո

-0.59

 ujednoznacz

-0.57

abestanden

-0.56

DataPropertyName

-0.55

 CreateTagHelper

-0.54

+#+

-0.50

 Mischung

-0.50

 vieill

-0.50

ynchronously

-0.49

POSITIVE LOGITS

 confines

1.47

 bounds

1.40

 boundaries

1.38

 scope

1.26

 borders

1.24

 limits

1.17

 purview

1.07

 parameters

1.04

boundaries

1.01

 walls

1.01

Activations Density 0.414%

phrases indicating limitations or constraints related to context or boundaries

No Comments

No Known Activations