INDEX

Explanations

references to programming frameworks and alert dialogs in code

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

 Chwiliwch

-0.61

 rzecz

-0.50

MENAFN

-0.48

stdc

-0.47

 zircon

-0.45

modelBuilder

-0.45

 borracha

-0.45

 Rasul

-0.45

enderror

-0.45

amycin

-0.45

POSITIVE LOGITS

SourceChecksum

1.04

InjectAttribute

0.74

TagHelpers

0.72

 lenker

0.68

 referrerpolicy

0.63

DeleteBehavior

0.62

 autorytatywna

0.57

UVWXYZ

0.56

 ExecuteAsync

0.56

 langue

0.54

Activations Density 0.159%

references to programming frameworks and alert dialogs in code

No Comments

No Known Activations