INDEX

Explanations

technical terms and programming-related concepts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B @ 40-gemmascope-res-16k

Configuration

google/gemma-scope-9b-pt-res/layer_40/width_16k/average_l0_125

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.40.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

outSlope

-0.35

TokenNameRBRACE

-0.34

 esternos

-0.33

 CEST

-0.33

 Wachs

-0.32

SequentialGroup

-0.32

níci

-0.32

UAS

-0.31

ⓘ

-0.31

 Bangor

-0.31

POSITIVE LOGITS

GV

1.22

HV

1.20

DV

1.20

PV

1.18

LV

1.16

pv

1.16

Cv

1.16

FV

1.15

NV

1.15

HV

1.14

Activations Density 3.615%

technical terms and programming-related concepts

No Comments

No Known Activations