INDEX

Explanations

items or categories related to classifications and counts in formal structures

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

ADVERTISEMENT

-0.64

theless

-0.59

 snuff

-0.58

RectangleBorder

-0.55

WriteLiteral

-0.54

tvguidetime

-0.53

 Thales

-0.52

 subgroup

-0.52

ACKNOWLEDGMENTS

-0.51

)|^{

-0.51

POSITIVE LOGITS

DockStyle

0.79

windowFixed

0.59

Personendaten

0.58

fromnode

0.57

bootstrapcdn

0.54

EDEFAULT

0.50

 koll

0.49

tagHelperRunner

0.49

 Italijanski

0.48

migrationBuilder

0.48

Activations Density 0.551%

items or categories related to classifications and counts in formal structures

No Comments

No Known Activations