INDEX

Explanations

discussions related to fairness and subjective opinions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 11-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_11/width_16k/average_l0_80

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.11.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

 Jefus

-1.02

 متعلقه

-0.95

 Paglinawan

-0.93

 виправивши

-0.93

 nahilalakip

-0.92

بوابة

-0.92

 ―――――

-0.91

 photolibrary

-0.90

$_"

-0.89

 auffi

-0.88

POSITIVE LOGITS

0.58

0.48

0.47

0.42

Whilst

0.41

ion

0.41

is

0.40

isn

0.38

 esta

0.38

 used

0.37

Activations Density 0.301%

discussions related to fairness and subjective opinions

No Comments

No Known Activations