INDEX

Explanations

mathematical symbols and formatting related to functions and equations

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

########.

-0.69

 BoxFit

-0.57

 inquirer

-0.53

 gynhyrchwyd

-0.51

timezone

-0.49

 ExecuteAsync

-0.48

 समीक्षक

-0.47

 Pend

-0.46

 Pent

-0.44

Hel

-0.44

POSITIVE LOGITS

 disambiguazione

0.84

tvguidetime

0.82

WebServlet

0.67

 <<<<<<<<<<<<<<

0.67

UnusedPrivate

0.64

mtrl

0.61

 Wiktionnaire

0.61

wickshire

0.60

herst

0.59

qrstuvwxyz

0.58

Activations Density 2.050%

mathematical symbols and formatting related to functions and equations

No Comments

No Known Activations