INDEX

Explanations

connections and relationships among organizations and their practices within industries

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

preceding topics or activities

np_acts-logits-general · gemini-2.0-flash

specific actions or outcomes

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

Something

-0.79

something

-0.76

somewhere

-0.71

 SOMETHING

-0.70

 something

-0.70

 thingy

-0.69

 Something

-0.69

 qualcosa

-0.69

Someone

-0.68

 somebody

-0.66

POSITIVE LOGITS

 relevant

1.29

key

1.14

 various

1.13

 important

1.09

 pertinent

1.07

 selected

1.06

 existing

1.05

 specific

0.99

 appropriate

0.96

 diverse

0.95

Activations Density 1.324%

connections and relationships among organizations and their practices within industries

preceding topics or activities

specific actions or outcomes

No Comments

No Known Activations