INDEX

Explanations

references to prediction and forecasts in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B @ 40-gemmascope-res-16k

Configuration

google/gemma-scope-9b-pt-res/layer_40/width_16k/average_l0_125

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.40.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

 Administrativna

-0.68

出版年

-0.45

JvmStatic

-0.42

AutoScaleMode

-0.40

choss

-0.36

 Italijanski

-0.35

berdayakan

-0.35

 lenker

-0.35

AppMethodBeat

-0.34

openzeppelin

-0.34

POSITIVE LOGITS

 prediction

3.36

 predictions

3.20

 predict

3.20

 predicting

3.14

 predicted

3.02

 predicts

2.98

 Prediction

2.97

 Predictions

2.80

Prediction

2.78

预测

2.72

Activations Density 1.833%

references to prediction and forecasts in various contexts

No Comments

No Known Activations