INDEX

Explanations

terms related to specific conditions, instructions, or functionalities in technical contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 6-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_6/width_16k/average_l0_70

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.6.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

fjspx

-0.69

||}

-0.62

)))));

-0.59

GOTREF

-0.56

IsMutable

-0.54

UnusedPrivate

-0.53

InjectAttribute

-0.51

ConstraintMaker

-0.50

 contextLoads

-0.49

Abp

-0.49

POSITIVE LOGITS

rrggbb

0.59

ArgsConstructor

0.58

.*")]

0.58

ếng

0.53

StrictMode

0.53

 bites

0.50

LEn

0.48

 regole

0.48

 Carmel

0.47

cloudflare

0.47

Activations Density 1.775%

terms related to specific conditions, instructions, or functionalities in technical contexts

No Comments

No Known Activations