INDEX

Explanations

terms related to mathematical proof and demonstration

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

SPJ

-0.50

unal

-0.49

 rozho

-0.46

gegeben

-0.45

emore

-0.45

toral

-0.45

 general

-0.44

NewUrlParser

-0.43

труд

-0.43

Choices

-0.43

POSITIVE LOGITS

Prove

1.24

 Prove

1.23

 prouver

1.16

 prouve

1.05

 proves

1.04

 proving

1.02

prove

1.01

 proofs

1.00

 proof

1.00

 Proving

0.99

Activations Density 0.509%

terms related to mathematical proof and demonstration

No Comments

No Known Activations