INDEX

Explanations

terms related to attributes in programming or markup languages

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

google/gemma-scope-2b-pt-res/layer_9/width_16k/average_l0_73

Prompts (Dashboard)

36,864 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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

بوابة

-0.97

Looper

-0.84

 marins

-0.81

 /\.(

-0.80

-0.77

 ReactDOM

-0.77

ChildScrollView

-0.77

Rujuakan

-0.76

 socialists

-0.76

 chrétiens

-0.76

POSITIVE LOGITS

 attributes

1.75

 attribute

1.66

attributes

1.58

 Attribute

1.51

 Attributes

1.49

Attribute

1.40

Attributes

1.39

attribute

1.35

setAttribute

1.26

addAttribute

1.26

Activations Density 0.079%

terms related to attributes in programming or markup languages

No Comments

No Known Activations