INDEX

Explanations

terms related to differences and variations between systems or approaches

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 11-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_11/width_16k/average_l0_80

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.11.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

pius

-0.49

poche

-0.40

 next

-0.39

laught

-0.39

 hiện

-0.38

]}>

-0.36

ランド

-0.36

arb

-0.35

 vừa

-0.35

da

-0.34

POSITIVE LOGITS

!*\

0.96

 differing

0.95

 variations

0.89

 Vary

0.88

 differed

0.86

 variation

0.84

 identical

0.83

IUrlHelper

0.82

 differences

0.81

 varying

0.80

Activations Density 0.805%

terms related to differences and variations between systems or approaches

No Comments

No Known Activations