INDEX

Explanations

phrases related to presence and alibi in a narrative context

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

lyon

-0.50

 '*')

-0.50

≦)

-0.49

Wen

-0.47

EREF

-0.47

 odpor

-0.46

esgue

-0.46

thod

-0.46

 selectivity

-0.46

 republicans

-0.46

POSITIVE LOGITS

 ready

0.80

tagHelperRunner

0.79

 صوتيه

0.74

StoryboardSegue

0.70

 there

0.70

 disambiguazione

0.66

省市镇

0.64

Przypisy

0.62

 externi

0.61

InjectAttribute

0.61

Activations Density 0.250%

phrases related to presence and alibi in a narrative context

No Comments

No Known Activations