INDEX

Explanations

terms related to weight and measurements 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-IT @ 9-gemmascope-res-16k

Configuration

google/gemma-scope-9b-it-res/layer_9/width_16k/average_l0_88

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.9.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

 للاسماء

-0.81

oredCriteria

-0.71

 Infórmanos

-0.70

 nonUne

-0.68

AddTagHelper

-0.67

IsMutable

-0.67

 doInBackground

-0.65

posedge

-0.65

 newBuilder

-0.63

 disambiguazione

-0.61

POSITIVE LOGITS

 weight

2.30

weight

2.22

Weight

2.20

 Weight

2.08

 WEIGHT

1.95

WEIGHT

1.90

 weights

1.84

weights

1.74

 Weights

1.68

 weigh

1.66

Activations Density 0.150%

terms related to weight and measurements in various contexts

No Comments

No Known Activations