INDEX

Explanations

terms related to database schema and components

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.5.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

SBATCH

-0.54

 ब्रेकडाउन

-0.50

دانشنامهٔ

-0.50

MathML

-0.47

 surla

-0.43

sulf

-0.42

 Wiktionnaire

-0.42

发表于

-0.42

 adal

-0.42

ništ

-0.41

POSITIVE LOGITS

 Administrativna

0.68

 Monfieur

0.66

 Jefus

0.65

Efq

0.64

contentLoaded

0.62

DIPSETTING

0.59

 iſt

0.58

 betweenstory

0.58

AddTagHelper

0.57

'},

0.56

Activations Density 1.090%

terms related to database schema and components

No Comments

No Known Activations