INDEX

Explanations

terms related to account verification processes

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.21.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

 pleaſure

-1.38

 houſe

-1.30

 itſelf

-1.30

 myſelf

-1.25

 ſever

-1.24

 purpoſe

-1.23

 ſta

-1.23

 Reſ

-1.21

 ſtate

-1.21

 ſche

-1.18

POSITIVE LOGITS

mga

0.61

0.60

en

0.60

0.59

«

0.58

di

0.58

0.57

Di

0.57

0.56

Activations Density 0.031%

terms related to account verification processes

No Comments

No Known Activations