INDEX

Explanations

elements related to proving concepts or claims within a structured argument

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

makeText

-0.67

mappedBy

-0.60

 awakeFromNib

-0.54

mlx

-0.52

таратура

-0.49

 canst

-0.48

#+#

-0.47

 Réalisation

-0.45

 resourceCulture

-0.44

posted

-0.44

POSITIVE LOGITS

 CreateTagHelper

0.72

 digress

0.62

 ExecuteAsync

0.62

Lets

0.61

+#+#

0.61

HasIndex

0.58

 defaultstate

0.57

Eloquent

0.57

 Lets

0.56

 lets

0.56

Activations Density 0.563%

elements related to proving concepts or claims within a structured argument

No Comments

No Known Activations