INDEX

Explanations

words associated with health conditions and their implications

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.3.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

bootstrapcdn

-1.00

 FetchType

-0.96

:✨

-0.95

QMetaType

-0.92

 AssemblyTitle

-0.90

InputBorder

-0.88

adaptiveStyles

-0.84

 Réponses

-0.83

pexpr

-0.82

quelize

-0.80

POSITIVE LOGITS

:]

1.33

:])

0.94

:],

0.78

:].

0.61

()]

0.59

Marshal

0.53

 Estatal

0.51

vud

0.48

:]:

0.46

()]

0.45

Activations Density 0.015%

words associated with health conditions and their implications

No Comments

No Known Activations