INDEX

Explanations

parameters and properties in a coding context

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.5.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

oa̍t

-0.71

aarrggbb

-0.59

 Shaksp

-0.55

 Shakspeare

-0.54

 betweenstory

-0.54

 omnium

-0.54

mcc

-0.51

RefNanny

-0.51

 incomplète

-0.51

 damskie

-0.50

POSITIVE LOGITS

Column

2.26

 Column

1.78

 column

1.42

column

1.32

 COLUMN

1.30

COLUMN

1.18

 Columns

1.06

 columns

1.04

 columna

1.02

 coluna

0.98

Activations Density 0.021%

parameters and properties in a coding context

No Comments

No Known Activations