INDEX

Explanations

terms related to health, conditions, and assessments within a medical context

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 1-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_1/width_16k/average_l0_102

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.1.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

每一个

-0.53

to

-0.51

μ

-0.48

 micro

-0.48

бяза

-0.47

 каждому

-0.47

 equipped

-0.47

ModelAndView

-0.47

or

-0.47

-0.46

POSITIVE LOGITS

ThroughAttribute

0.87

NameInMap

0.75

 Jefus

0.75

webElementXpaths

0.73

AccessorTable

0.71

 mergeFrom

0.71

Fot

0.70

 bezeichneter

0.68

 myſelf

0.68

 jsPsych

0.67

Activations Density 0.092%

terms related to health, conditions, and assessments within a medical context

No Comments

No Known Activations