INDEX

Explanations

terms related to medical and healthcare treatments

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.12.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

 Italijani

-0.65

➟

-0.61

Spoljašnje

-0.58

تفصیلات

-0.57

Jeografia

-0.55

govina

-0.54

appé

-0.53

 Meksiku

-0.53

EndGlobalSection

-0.52

JspWriter

-0.51

POSITIVE LOGITS

 itſelf

0.78

 faſt

0.75

 ſever

0.73

 preſent

0.70

 iſt

0.69

 ſche

0.68

 leaſt

0.68

Efq

0.63

 pleaſure

0.63

Eſ

0.63

Activations Density 1.515%

terms related to medical and healthcare treatments

No Comments

No Known Activations