INDEX

Explanations

technical and scientific terminology related to biomedical processes and measurements

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

sites, reduction, process

np_acts-logits-general · gemini-2.5-flash-lite

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 16-gemmascope-res-65k

Configuration

google/gemma-scope-2b-pt-res/layer_16/width_65k/average_l0_128

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

65,536

Data Type

float32

Hook Name

blocks.16.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

이션

-0.55

GTCX

-0.54

ivasan

-0.48

DoubleQuotes

-0.47

moveToFirst

-0.46

ChildScrollView

-0.45

stdc

-0.45

 trajets

-0.44

AddTagHelper

-0.44

basicConfig

-0.43

POSITIVE LOGITS

 của

0.75

ของ

0.66

of

0.64

BASEPATH

0.62

sizeCache

0.59

]")]

0.58

utilisons

0.57

saraba

0.54

LookAnd

0.54

abinieri

0.53

Activations Density 0.619%

technical and scientific terminology related to biomedical processes and measurements

sites, reduction, process

No Comments

No Known Activations