INDEX

Explanations

terms related to explosions and eruptive actions

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

ristan

-0.49

usap

-0.49

nake

-0.48

piac

-0.47

 Grunde

-0.47

ridos

-0.47

Dre

-0.47

 privilegi

-0.46

ண்

-0.46

 diligently

-0.46

POSITIVE LOGITS

 explosion

1.54

 burst

1.51

 exploding

1.43

 explosions

1.42

 explodes

1.42

 bursting

1.42

 bursts

1.41

 erup

1.40

 explode

1.39

 eruption

1.37

Activations Density 0.283%

terms related to explosions and eruptive actions

No Comments

No Known Activations