INDEX

Explanations

terms related to predictions and forecasting in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 13-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_13/width_16k/average_l0_84

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.13.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 pinggang

-0.67

 dalamnya

-0.63

 circ

-0.59

aldehyde

-0.59

memberId

-0.59

astricht

-0.59

circ

-0.58

Cha

-0.57

whatsapp

-0.57

руппа

-0.56

POSITIVE LOGITS

 Predict

1.38

 predict

1.38

 prediction

1.32

 predictions

1.32

 predicts

1.30

 Predictions

1.25

 Prediction

1.25

 PRED

1.24

Predict

1.22

 Predic

1.21

Activations Density 0.094%

terms related to predictions and forecasting in various contexts

No Comments

No Known Activations