INDEX

Explanations

numeric values and identifiers

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

-0.71

 EconPapers

-0.56

-0.53

xxxxxxxxxxxxxxxx

-0.53

merate

-0.50

GraphicsUnit

-0.50

usercontent

-0.48

ercito

-0.48

IBAction

-0.47

xx

-0.47

POSITIVE LOGITS

WriteLiteral

0.67

 بيها

0.52

quelize

0.50

 للمعارف

0.47

Filmografia

0.47

μβρίου

0.46

 Numerade

0.45

initializeApp

0.45

vece

0.45

idation

0.44

Activations Density 0.358%

numeric values and identifiers

No Comments

No Known Activations