INDEX

Explanations

technical terms and jargon related to engineering and programming

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

FF

-1.31

Ff

-1.25

FF

-1.20

Ff

-1.17

MF

-1.15

PF

-1.13

LF

-1.12

 getF

-1.12

WF

-1.09

TF

-1.08

POSITIVE LOGITS

 useAppContext

0.36

 Nicho

0.34

ặn

0.33

 Ingram

0.32

 LCCN

0.32

 Knie

0.32

▫

0.31

ցված

0.31

AddTagHelper

0.31

utriche

0.31

Activations Density 8.655%

technical terms and jargon related to engineering and programming

No Comments

No Known Activations