INDEX

Explanations

references to individuals and their actions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.3.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

GraphicsUnit

-0.89

Efq

-0.69

CloseOperation

-0.65

 Theſe

-0.63

SourceChecksum

-0.62

 censiti

-0.62

cookieParser

-0.60

Portale

-0.58

 ſeveral

-0.57

CELLANEOUS

-0.57

POSITIVE LOGITS

'{@

0.69

ⓧ

0.60

whom

0.59

 آنچه

0.58

 Wikimedijinoj

0.58

 whom

0.56

 którą

0.55

 auquel

0.54

 auxquels

0.54

 kterou

0.53

Activations Density 0.217%

references to individuals and their actions

No Comments

No Known Activations