INDEX

Explanations

questions and expressions related to needs and expectations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 7-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_7/width_16k/average_l0_69

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.7.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

 Preferred

-0.52

 preferred

-0.52

 Nicolson

-0.49

preferred

-0.49

HandlerContext

-0.48

 AssemblyTitle

-0.48

Preferred

-0.47

simov

-0.47

usepackage

-0.46

dsa

-0.45

POSITIVE LOGITS

THING

1.01

 things

0.89

 something

0.88

 stuff

0.88

 THING

0.88

 thing

0.87

 everything

0.84

的东西

0.83

Demografie

0.83

anything

0.82

Activations Density 0.528%

questions and expressions related to needs and expectations

No Comments

No Known Activations