INDEX

Explanations

terms related to educational and healthcare professions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 4-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_4/width_16k/average_l0_124

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.4.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

-0.73

setVerticalGroup

-0.68

onAttach

-0.67

 ExecuteAsync

-0.66

########.

-0.62

umably

-0.62

Referències

-0.61

/\.

-0.59

最快更新

-0.58

ringer

-0.57

POSITIVE LOGITS

 engineer

0.99

 engineers

0.92

 Engineer

0.90

Engineer

0.87

Engineers

0.86

 Engineers

0.85

engineer

0.85

titian

0.82

 ingenieros

0.80

 ENGINEER

0.75

Activations Density 1.055%

terms related to educational and healthcare professions

No Comments

No Known Activations