INDEX

Explanations

programming-related keywords and constructs

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B @ 8-gemmascope-res-16k

Configuration

google/gemma-scope-9b-pt-res/layer_8/width_16k/average_l0_99

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.8.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

WriteBarrier

-0.76

 '\\;'

-0.74

AccessorTable

-0.73

BagConstraints

-0.72

OGND

-0.72

WriteTagHelper

-0.71

DIPSETTING

-0.70

 Normdatei

-0.70

 GenerationType

-0.68

UnusedPrivate

-0.67

POSITIVE LOGITS

TokenNameLBRACE

0.33

sin

0.32

 relative

0.32

Coordonnées

0.30

Information

0.29

slo

0.28

ths

0.28

 coinc

0.28

 financial

0.28

file

0.28

Activations Density 0.535%

programming-related keywords and constructs

No Comments

No Known Activations