INDEX

Explanations

references to systems, layouts, or configurations related to items and their placement constraints

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 23-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_23/width_16k/average_l0_75

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.23.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

webElementXpaths

-0.75

 Италијани

-0.75

 kaarangay

-0.73

UserScript

-0.71

 Italijanski

-0.69

 podjela

-0.69

 Biôgrafia

-0.65

Демографія

-0.65

™.

-0.65

 "..\..\

-0.64

POSITIVE LOGITS

 again

0.65

to

0.60

of

0.57

in

0.55

on

0.52

again

0.49

 with

0.48

同上

0.48

 Again

0.47

by

0.47

Activations Density 0.482%

references to systems, layouts, or configurations related to items and their placement constraints

No Comments

No Known Activations