INDEX

Explanations

references to specific studies involving rats

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.3.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

 jugu

-0.63

adecimal

-0.63

umpul

-0.63

mités

-0.62

 dispen

-0.59

 frow

-0.58

 photolibrary

-0.58

fiscal

-0.55

avares

-0.55

 yaka

-0.55

POSITIVE LOGITS

rat

1.05

ani

1.03

ISupport

1.01

Rat

0.91

StoryboardSegue

0.91

rat

0.89

 rats

0.87

cre

0.86

 препратки

0.85

Rat

0.85

Activations Density 0.423%

references to specific studies involving rats

No Comments

No Known Activations