INDEX

Explanations

references to specific medical terms related to blood or serum analysis

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 0-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_0/width_16k/average_l0_105

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.0.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

 Frankel

-0.61

下载附件

-0.57

fx

-0.56

curacies

-0.56

li

-0.55

bon

-0.54

 padre

-0.54

خرى

-0.53

WithFormat

-0.51

なた

-0.51

POSITIVE LOGITS

DS

1.11

ds

0.98

SS

0.90

TS

0.87

CS

0.77

IsMutable

0.74

NS

0.74

DS

0.71

helial

0.70

rawDesc

0.69

Activations Density 0.127%

references to specific medical terms related to blood or serum analysis

No Comments

No Known Activations