INDEX

Explanations

references to software, programming, or technical specifications

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

StoryboardSegue

-0.74

ons

-0.47

row

-0.47

 للمعارف

-0.46

 Show

-0.46

önen

-0.45

nextInt

-0.44

ioutil

-0.44

UserScript

-0.44

row

-0.44

POSITIVE LOGITS

تقاوى

0.81

MigrationBuilder

0.57

PyExc

0.56

 considérons

0.52

ValueStyle

0.51

cticut

0.50

DOCTYPE

0.49

richTextPanel

0.48

tidaknya

0.47

 Zacks

0.47

Activations Density 0.717%

references to software, programming, or technical specifications

No Comments

No Known Activations