INDEX

Explanations

terms related to medical conditions and treatments

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 13-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_13/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.13.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

oubliez

-0.46

úrese

-0.45

featureID

-0.43

 both

-0.43

Ak

-0.41

xtures

-0.40

God

-0.40

not

-0.40

top

-0.39

POSITIVE LOGITS

 itſelf

0.93

 myſelf

0.83

 مرئيه

0.81

 themſelves

0.81

 ordinaria

0.77

 himſelf

0.76

 elsewhere

0.74

 againſt

0.72

 Reſ

0.72

ſelf

0.72

Activations Density 1.486%

terms related to medical conditions and treatments

No Comments

No Known Activations