INDEX

Explanations

structured data or objects within a specific formatting context, such as JSON-like structures

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 13-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_13/width_16k/average_l0_84

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.13.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

 المعيارى

-0.94

RenderAtEndOf

-0.65

ьаж

-0.64

 framför

-0.57

Externé

-0.55

 themselves

-0.54

PerformLayout

-0.54

 scolaire

-0.53

 exécu

-0.53

 EClass

-0.52

POSITIVE LOGITS

awtextra

0.64

tagHelperRunner

0.63

 disambiguazione

0.62

FormTagHelper

0.59

AccessorTable

0.57

Autoritní

0.57

Jeho

0.50

 Krim

0.50

 Beatles

0.49

"]();

0.49

Activations Density 0.469%

structured data or objects within a specific formatting context, such as JSON-like structures

No Comments

No Known Activations