INDEX

Explanations

references to academic achievements and awards

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 0-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_0/width_16k/average_l0_105

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.0.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

setVerticalGroup

-1.29

OGND

-1.07

Personendaten

-0.95

 autorytatywna

-0.87

MigrationBuilder

-0.85

 AssemblyProduct

-0.82

✨:

-0.82

()")

-0.81

:✨

-0.81

 Numerade

-0.81

POSITIVE LOGITS

sion

0.90

sions

0.74

Maj

0.62

Maj

0.54

idenav

0.50

contrib

0.50

sional

0.49

bių

0.46

遮

0.45

Activations Density 0.158%

references to academic achievements and awards

No Comments

No Known Activations