INDEX

Explanations

terms related to software licensing and legal disclaimers

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.12.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

Efq

-0.54

 Monfieur

-0.49

 Theſe

-0.48

 ſeveral

-0.48

 purpoſe

-0.47

 myſelf

-0.45

^(@)

-0.45

 Majefty

-0.44

 Jefus

-0.44

 becauſe

-0.43

POSITIVE LOGITS

<bos>

0.93

<eos>

0.32

ро

0.29

MathML

0.29

нен

0.29

’

0.29

ρυ

0.28

ih

0.28

â

0.28

р

0.28

Activations Density 44.600%

terms related to software licensing and legal disclaimers

No Comments

No Known Activations

terms related to software licensing and legal disclaimers

No Comments

No Known Activations