INDEX

Explanations

medical or legal terms related to patient conditions and treatment

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.18.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

󠁿

-0.70

".

-0.70

).

-0.69

”.

-0.68

 שוליים

-0.65

}}$.

-0.64

“.

-0.63

}$.

-0.60

-0.59

'.

-0.59

POSITIVE LOGITS

any

1.02

 quelconque

0.95

 anything

0.94

anything

0.93

ANY

0.82

的话

0.78

 quelcon

0.78

Any

0.77

ใด

0.76

didSet

0.75

Activations Density 0.327%

medical or legal terms related to patient conditions and treatment

No Comments

No Known Activations