INDEX

Explanations

references to edges in graph theory

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

 مرئيه

-0.62

 dieux

-0.61

softc

-0.58

')))

-0.58

וקה

-0.57

 spazi

-0.57

})}\

-0.56

SEVERE

-0.55

 muối

-0.54

hoppers

-0.54

POSITIVE LOGITS

 edges

1.17

 Edges

1.05

Edges

0.91

RectangleBorder

0.84

edges

0.82

AnchorStyles

0.65

 edging

0.63

 congratulate

0.61

 hints

0.60

 sugi

0.60

Activations Density 0.061%

references to edges in graph theory

No Comments

No Known Activations