INDEX

Explanations

references to educational or instructional content

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 13-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_13/width_16k/average_l0_84

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.13.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

 Monfieur

-1.19

Efq

-1.19

 itſelf

-1.15

 Jefus

-1.10

 myſelf

-1.10

 ―――――

-1.06

 photolibrary

-1.03

 Majefty

-1.01

 Theſe

-1.00

ſelves

-0.99

POSITIVE LOGITS

0.59

 comment

0.58

 note

0.57

0.56

<eos>

0.54

Note

0.53

 comments

0.52

 Note

0.51

by

0.51

note

0.51

Activations Density 1.291%

references to educational or instructional content

No Comments

No Known Activations