INDEX

Explanations

terms related to clinical trial findings and efficacy evaluations

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

 strange

-0.49

Strange

-0.49

DUE

-0.49

-0.48

loc

-0.48

 const

-0.47

cha

-0.47

 page

-0.46

strange

-0.45

lə

-0.44

POSITIVE LOGITS

 uſed

0.86

 quæ

0.83

Efq

0.83

 calendriers

0.77

WithIOException

0.76

AddTagHelper

0.76

AndEndTag

0.75

 raiſ

0.75

 Majefty

0.73

 auffi

0.72

Activations Density 2.133%

terms related to clinical trial findings and efficacy evaluations

No Comments

No Known Activations