INDEX

Explanations

mathematical and statistical terms related to products and sums within expressions and expansions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.5.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

 للاسماء

-0.68

 disambiguazione

-0.66

 Reſ

-0.62

 UIColor

-0.61

ysuckle

-0.61

 leſs

-0.61

жнему

-0.59

 ModelRenderer

-0.59

inheit

-0.58

KEYCODE

-0.57

POSITIVE LOGITS

곱

0.72

∏

0.72

ftagPool

0.68

Multiply

0.64

 tích

0.63

unsplash

0.58

SerializedSize

0.56

积

0.54

 Multiply

0.53

 multiply

0.52

Activations Density 0.798%

mathematical and statistical terms related to products and sums within expressions and expansions

No Comments

No Known Activations