INDEX

Explanations

references 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 @ 12-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.12.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

 marins

-0.85

بوابة

-0.80

Looper

-0.79

 BorderRadius

-0.75

-0.74

 Safer

-0.73

 jScrollPane

-0.73

 fuoco

-0.73

 Sailor

-0.73

 chrétiens

-0.72

POSITIVE LOGITS

 attributes

1.69

 attribute

1.66

attributes

1.55

Attribute

1.51

 Attribute

1.50

attribute

1.46

 Attributes

1.43

Attributes

1.35

setAttribute

1.27

addAttribute

1.27

Activations Density 0.058%

references to attributes in programming or markup languages

No Comments

No Known Activations