INDEX

Explanations

actions related to decision-making processes

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

google/gemma-scope-9b-pt-res/layer_2/width_16k/average_l0_67

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.2.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

makeConstraints

-0.48

autoreleasepool

-0.44

 become

-0.44

立

-0.41

ab

-0.41

 оказыва

-0.40

 deaf

-0.39

 prompt

-0.38

각주

-0.38

imp

-0.36

POSITIVE LOGITS

 Mechanism

0.62

 desmotivaciones

0.61

Mechanism

0.60

colgante

0.59

 leão

0.58

 Mechanisms

0.57

 impress

0.57

 للاسماء

0.57

mechanism

0.56

TypedDataSet

0.55

Activations Density 0.117%

actions related to decision-making processes

No Comments

No Known Activations