INDEX

Explanations

the word "ins" and its variations, indicating a focus on institutional or insider contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 25-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_25/width_16k/average_l0_116

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.25.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

CodeAttribute

-0.61

 CreateTagHelper

-0.59

initializeApp

-0.57

 Dostupné

-0.55

 comuniques

-0.55

انجليز

-0.55

 externi

-0.53

躇

-0.53

قایناق‌لار

-0.52

Personensuche

-0.51

POSITIVE LOGITS

 ExecuteAsync

0.57

omni

0.54

AndEndTag

0.50

 متعلقه

0.47

PullParser

0.47

oa̍t

0.46

ULATOR

0.46

CodedInputStream

0.46

TALL

0.45

WebKit

0.44

Activations Density 0.232%

the word "ins" and its variations, indicating a focus on institutional or insider contexts

No Comments

No Known Activations