INDEX

Explanations

mathematical symbols and notations commonly used in formal proofs

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 1-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_1/width_16k/average_l0_102

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.1.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

 ilman

-0.72

 näytte

-0.67

 BrowserModule

-0.66

 depositphotos

-0.66

HandlerContext

-0.65

 greateſt

-0.65

 Chaldean

-0.65

 tận

-0.63

WhereInput

-0.62

 Schenectady

-0.61

POSITIVE LOGITS

ea

0.76

ell

0.70

pri

0.61

TagHelper

0.57

ell

0.57

AnchorStyles

0.55

Ea

0.55

bis

0.55

sel

0.54

па

0.51

Activations Density 1.825%

mathematical symbols and notations commonly used in formal proofs

No Comments

No Known Activations