INDEX

Explanations

information related to official registrations and organizational details

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

 محفوظة

-0.74

izr

-0.54

UTERS

-0.48

 snippetHide

-0.46

клопе

-0.45

neurial

-0.45

databind

-0.44

 نب

-0.44

yntaxException

-0.43

AndEndTag

-0.43

POSITIVE LOGITS

<>());

0.63

Filmographie

0.62

ModelSerializer

0.62

 EconPapers

0.60

MigrationBuilder

0.59

Personendaten

0.59

 Jenderal

0.59

transQ

0.57

OnInit

0.56

REEN

0.56

Activations Density 1.836%

information related to official registrations and organizational details

No Comments

No Known Activations