INDEX

Explanations

words related to choosing or selection processes

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 13-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_13/width_16k/average_l0_84

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.13.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

Goodnight

-0.68

 InkWell

-0.62

 Bell

-0.61

σταση

-0.60

 Pedersen

-0.60

 '../

-0.60

etcode

-0.60

documented

-0.57

Graf

-0.56

bő

-0.56

POSITIVE LOGITS

choose

1.34

 choose

1.30

 choosing

1.30

 Choose

1.29

Choose

1.28

 chosen

1.26

 CHOOSE

1.26

choosing

1.25

 chooses

1.24

chosen

1.19

Activations Density 0.124%

words related to choosing or selection processes

No Comments

No Known Activations