INDEX

Explanations

terms related to experimental trials and statistical methods

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

 ever

-0.52

↵↵

-0.51

-0.46

 multi

-0.44

 δια

-0.43

marginVertical

-0.43

vi

-0.42

cl

-0.41

-0.40

 continued

-0.40

POSITIVE LOGITS

 myſelf

1.17

 itſelf

1.17

 houſe

1.14

 AssemblyCulture

1.11

 themſelves

1.09

 Jefus

1.05

 الرياضيه

1.04

 ſtate

1.03

 pleaſure

1.02

 Monfieur

0.99

Activations Density 0.584%

terms related to experimental trials and statistical methods

No Comments

No Known Activations