INDEX

Explanations

terms related to inspections and evaluations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 8-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_8/width_16k/average_l0_71

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.8.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

-0.67

vol

-0.58

-0.57

-0.55

-0.51

mu

-0.51

Mil

-0.51

Mu

-0.51

θρω

-0.50

POSITIVE LOGITS

 inspecting

1.31

 inspect

1.23

 inspec

1.20

 inspection

1.19

 Inspect

1.16

 inspected

1.14

 inspections

1.14

inspection

1.08

 examine

1.06

 examining

1.05

Activations Density 0.762%

terms related to inspections and evaluations

No Comments

No Known Activations