INDEX

Explanations

references to political entities and events

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 22-gemmascope-mlp-16k

Configuration

google/gemma-scope-2b-pt-mlp/layer_22/width_16k/average_l0_121

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.22.hook_mlp_out

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

aarrggbb

-0.68

+#+#

-0.61

 المعيارى

-0.57

 متعلقه

-0.56

 AssemblyCulture

-0.54

InstrumentedTest

-0.53

yntaxException

-0.51

 MaterialApp

-0.50

setPointSize

-0.50

 CanadaChoose

-0.49

POSITIVE LOGITS

 centre

0.61

verifyException

0.59

 centro

0.58

MigrationBuilder

0.54

 مواليد

0.53

شكرا

0.53



0.52

 center

0.52

 يتيمه

0.52

Diwedd

0.52

Activations Density 0.209%

references to political entities and events

No Comments

No Known Activations