INDEX

Explanations

phrases relating to risk and its consequences

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

preceding negative outcomes

np_acts-logits-general · gemini-2.0-flash

before + negative outcome

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 24-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_24/width_16k/average_l0_73

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.24.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

тувати

-0.64

Offering

-0.62

 Providing

-0.61

IUrlHelper

-0.60

Providing

-0.59

providing

-0.58

 Allows

-0.58

Provide

-0.57

 Provides

-0.57

 sends

-0.56

POSITIVE LOGITS

 falling

1.35

 coming

1.24

 becoming

1.20

 arriving

1.19

 dying

1.19

 disappearing

1.14

 losing

1.11

 winning

1.10

 getting

1.09

 failing

1.05

Activations Density 0.436%

phrases relating to risk and its consequences

preceding negative outcomes

before + negative outcome

No Comments

No Known Activations