INDEX

Explanations

numerical data or statistics related to clinical or medical metrics

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 10-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_10/width_16k/average_l0_77

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.10.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

JoinTable

-0.60

âteau

-0.55

Παραπομπές

-0.55

granate

-0.55

ända

-0.54

LabelTagHelper

-0.52

kirch

-0.51

ReusableCell

-0.51

alium

-0.50

はじめに

-0.50

POSITIVE LOGITS

 itſelf

0.66

 AssemblyProduct

0.62

참고

0.61

 myſelf

0.54

filas

0.51

 njia

0.50

 pleaſure

0.50

TintMode

0.50

 thereupon

0.50

UnknownFields

0.49

Activations Density 1.165%

numerical data or statistics related to clinical or medical metrics

No Comments

No Known Activations