INDEX

Explanations

references to scientific and statistical concepts

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

ils

-0.61

les

-0.57

vado

-0.51

‘

-0.51

IVED

-0.50

Check

-0.49

lr

-0.49

me

-0.49

POSITIVE LOGITS

Datuak

1.08

CloseOperation

0.86

########.

0.85

ParallelGroup

0.85

<bos>

0.82

queryInterface

0.81

WithIOException

0.78

 initComponents

0.77

 autorytatywna

0.77

MLLoader

0.76

Activations Density 0.252%

references to scientific and statistical concepts

No Comments

No Known Activations