INDEX

Explanations

occurrences of programming keywords related to class visibility and function definitions

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

 TextAppearance

-0.60

zeß

-0.52

ី

-0.50

ilitate

-0.48

istes

-0.47

 Herr

-0.47

Singh

-0.45

 retrograde

-0.44

 singh

-0.44

dious

-0.43

POSITIVE LOGITS

public

1.42

 public

1.12

Public

1.12

 publique

1.05

 للاسماء

1.04

 Public

1.04

fjspx

1.03

 PUBLIC

1.00

awtextra

0.95

 الاطلاع

0.93

Activations Density 0.025%

occurrences of programming keywords related to class visibility and function definitions

No Comments

No Known Activations