INDEX

Explanations

references to annotations in programming or data structures

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 7-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_7/width_16k/average_l0_69

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.7.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

IndentedString

-0.89

Personensuche

-0.80

TypedDataSet

-0.76

 незавершена

-0.73

 makeStyles

-0.72

 beginnetje

-0.72

expandindo

-0.68

amazonaws

-0.67

 NgModule

-0.66

__*/

-0.65

POSITIVE LOGITS

annotation

0.88

enumi

0.72

AnchorStyles

0.64

 bezeichneter

0.62

Diweddarwch

0.62

annotations

0.60

 noten

0.59

הערות

0.59

 nhiêu

0.58

 Royce

0.57

Activations Density 0.003%

references to annotations in programming or data structures

No Comments

No Known Activations