INDEX

Explanations

terms related to criteria for medical exclusion and references to death

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 14-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_14/width_16k/average_l0_84

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.14.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

 domes

-0.62

ETHING

-0.56

savevideo

-0.53

<bos>

-0.53

 newVal

-0.52

 champs

-0.52

cursion

-0.52

 ſtill

-0.52

sth

-0.52

apatilla

-0.51

POSITIVE LOGITS

 predeceased

0.78

 صوتيه

0.75

LayoutConstraint

0.68

 محفوظة

0.63

onAttach

0.62

TargetException

0.60

HasForeignKey

0.59

HostException

0.57

ElementException

0.56

 kasarigan

0.54

Activations Density 0.011%

terms related to criteria for medical exclusion and references to death

No Comments

No Known Activations