INDEX

Explanations

variables and their attributes 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 @ 4-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_4/width_16k/average_l0_124

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.4.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

‍

-0.43

íncipe

-0.42

 quien

-0.41

Don

-0.41

et

-0.41

-0.40

-0.39

readAs

-0.39

 wurden

-0.39

POSITIVE LOGITS

 pleaſure

0.96

 kasarigan

0.88

 raiſ

0.88

 المعيارى

0.85

 purpoſe

0.85

Sucesor

0.84

WebVitals

0.82

IsInitialized

0.82

 itſelf

0.81

Activations Density 0.210%

variables and their attributes in code

No Comments

No Known Activations