INDEX

Explanations

terms and phrases related to causal relationships and causal inference models

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

Token "ca" or "Ca" followed by specific letters

np_acts-logits-general · gemini-2.0-flash

causal, capable

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.18.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

 للمعارف

-1.14

 برانيه

-0.90

iocene

-0.87

romptu

-0.82

 Савезне

-0.82

Geplaatst

-0.81

 EconPapers

-0.77

cticut

-0.76

Rptr

-0.74

]()

-0.73

POSITIVE LOGITS

Ca

0.94

Ca

0.92

ca

0.86

ca

0.78

 Cahill

0.75

CA

0.72

 Caul

0.67

CA

0.64

Captor

0.63

 caul

0.54

Activations Density 0.220%

terms and phrases related to causal relationships and causal inference models

Token "ca" or "Ca" followed by specific letters

causal, capable

No Comments

No Known Activations