INDEX

Explanations

terms related to receiving or acknowledgment within a context

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

 StringTokenizer

-0.59

 whiteColor

-0.49

InputBorder

-0.49

 utafitiHapana

-0.48

 AppCompatTheme

-0.48

TagMode

-0.48

EndProject

-0.47

 متعلقه

-0.47

letic

-0.47

évaluateur

-0.46

POSITIVE LOGITS

 receiving

2.95

 Receiving

2.80

 receive

2.69

 RECE

2.69

Receiving

2.67

 receiver

2.66

 recie

2.59

receiving

2.56

receive

2.53

 Receive

2.52

Activations Density 0.251%

terms related to receiving or acknowledgment within a context

No Comments

No Known Activations