INDEX

Explanations

punctuation and symbols used in code

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-131k

Configuration

google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

131,072

Data Type

float32

Hook Name

blocks.20.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

 initComponents

-0.94

########.

-0.93

 المعيارى

-0.91

parsedMessage

-0.88

ftagPool

-0.88

<unused52>

-0.85

MLLoader

-0.85

<unused28>

-0.85

<unused17>

-0.85

<unused8>

-0.85

POSITIVE LOGITS

<eos>

0.30

0.29

ENODEV

0.27

 médicament

0.27

Kön

0.26

Olvid

0.25

上

0.25

),

0.25

 neby

0.24

 when

0.23

Activations Density 0.062%

punctuation and symbols used in code

No Comments

No Known Activations