INDEX

Explanations

references to specific characters or entities within a narrative context

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B @ 13-gemmascope-res-16k

Configuration

google/gemma-scope-9b-pt-res/layer_13/width_16k/average_l0_132

Prompts (Dashboard)

24,576 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

ंदीखरीदारी

-0.66

 referrerpolicy

-0.65

TryDecodeAsNil

-0.63

 ब्रेकडाउन

-0.63

Tikang

-0.63

expandindo

-0.61

 queſta

-0.60

🜲

-0.60

BibitemShut

-0.60

Rujuakan

-0.60

POSITIVE LOGITS

accumulative

0.33

 sürd

0.33

accompag

0.32

 sortant

0.31

 izquierdo

0.31

 toer

0.31

 parcialmente

0.30

 réaliste

0.30

 bañ

0.30

 abandonné

0.30

Activations Density 0.489%

references to specific characters or entities within a narrative context

No Comments

No Known Activations