INDEX

Explanations

references to bus transportation

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

 cielos

-0.65

teht

-0.58

 moulin

-0.57

ések

-0.56

 pétrole

-0.56

Calais

-0.56

 Einf

-0.54

ParallelGroup

-0.54

 caoutchouc

-0.54

 acrylique

-0.54

POSITIVE LOGITS

bus

4.72

Bus

4.41

Bus

4.30

bus

4.26

 buses

3.66

BUS

3.65

BUS

3.52

 Buses

3.28

buses

2.82

Buses

2.81

Activations Density 0.045%

references to bus transportation

No Comments

No Known Activations