INDEX

Explanations

mathematical symbols, particularly those indicating equations or mathematical relationships

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-65k

Configuration

google/gemma-scope-2b-pt-res/layer_12/width_65k/average_l0_72

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

65,536

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

 يتيمه

-1.00

NDL

-0.84

 دیکھیے

-0.78

endes

-0.71

NewRow

-0.71

RenderAtEndOf

-0.69

GEBURTSDATUM

-0.69

 Mendes

-0.68

 wireType

-0.68

 basta

-0.67

POSITIVE LOGITS

1.05

$\

0.99

$\

0.97

"\

0.94

($\

0.84

mRecyclerView

0.82

#\

0.81

middels

0.79

("\

0.78

$$\

0.78

Activations Density 0.129%

mathematical symbols, particularly those indicating equations or mathematical relationships

No Comments

No Known Activations