INDEX

Explanations

references to programming functions and modules

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B @ 35-gemmascope-res-16k

Configuration

google/gemma-scope-9b-pt-res/layer_35/width_16k/average_l0_120

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.35.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

+#+#

-0.47

ⓧ

-0.44

DockStyle

-0.40

 algodón

-0.36

 فريبيس

-0.35

 dudas

-0.34

enderror

-0.33

 doubts

-0.32

 rhestr

-0.30

 Zweifel

-0.30

POSITIVE LOGITS

sap

0.72

sap

0.69

⇶

0.60

 sapon

0.59

 الحره

0.58

Sap

0.57

SAP

0.55

FLP

0.55

Sab

0.54

Bril

0.54

Activations Density 0.203%

references to programming functions and modules

No Comments

No Known Activations