INDEX

Explanations

references to height 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

 wireType

-0.44

createStatement

-0.41

execSQL

-0.39

 mxArray

-0.39

prepareStatement

-0.38

ulink

-0.38

دانشنامهٔ

-0.38

 estrenar

-0.36

InitVars

-0.36

 unwritten

-0.36

POSITIVE LOGITS

 height

2.45

 Height

2.28

height

2.22

Height

2.13

 heights

1.93

 HEIGHT

1.92

HEIGHT

1.76

 altura

1.74

heights

1.64

 getHeight

1.60

Activations Density 0.167%

references to height measurements in various contexts

No Comments

No Known Activations