INDEX

Explanations

terms related to mathematical concepts, particularly in topology and algebra

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

-0.51

Diweddarwch

-0.51

 kanton

-0.50

ActiveRecord

-0.48

Smart

-0.47

Master

-0.47

 راه

-0.46

rrggbb

-0.46

ja

-0.45

POSITIVE LOGITS

 pleaſure

1.06

 myſelf

1.02

 itſelf

0.94

 Theſe

0.94

 themſelves

0.88

 Monfieur

0.88

 ſeveral

0.87

 purpoſe

0.87

 Jefus

0.85

 preſent

0.83

Activations Density 3.337%

terms related to mathematical concepts, particularly in topology and algebra

No Comments

No Known Activations