INDEX

Explanations

medical or scientific terminology related to conditions or treatments

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

 المعيارى

-0.64

WriteBarrier

-0.59

ensaft

-0.57

 للمعارف

-0.57

:+:

-0.57



-0.56

devamını

-0.52

 متعلقه

-0.51

__*/

-0.51

urnal

-0.51

POSITIVE LOGITS

III

0.67

 numbered

0.64

第

0.62

numbered

0.62

III

0.60

 numbering

0.58

irability

0.57

第

0.55

II

0.53

endphp

0.52

Activations Density 1.103%

medical or scientific terminology related to conditions or treatments

No Comments

No Known Activations