INDEX

Explanations

questions related to uncertainty and potential outcomes

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

preceding "happen" or its inflections

np_acts-logits-general · gemini-2.0-flash

what will happen

np_acts-logits-general · gemini-2.5-flash-lite

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.22.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

ControllerTest

-0.67

tometer

-0.61

PostExecute

-0.55

 ComVisible

-0.53

 Jacobi

-0.53

 Presbyter

-0.53

efeller

-0.53

COMPLEX

-0.52

WithIOException

-0.50

 Reiter

-0.50

POSITIVE LOGITS

 happen

2.75

 happens

2.50

 happened

2.48

 happening

2.31

happen

2.19

 Happen

2.19

happens

2.06

happened

2.01

 HAPP

2.00

 Happens

1.98

Activations Density 0.271%

questions related to uncertainty and potential outcomes

preceding "happen" or its inflections

what will happen

No Comments

No Known Activations