INDEX

Explanations

patterns and structures in computer code

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 11-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_11/width_16k/average_l0_80

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.11.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

 Estrada

-0.56

ić

-0.55

Ger

-0.55

gry

-0.54

-0.53

 силы

-0.53

mol

-0.52

 heng

-0.52

reg

-0.52

POSITIVE LOGITS

 myſelf

1.13

 Houſe

1.11

 fubject

1.10

 againſt

1.09

Eſ

1.07

 quæ

1.07

 chofe

1.06

 Wiktionnaire

1.05

 raiſ

1.04

 becauſe

1.03

Activations Density 0.093%

patterns and structures in computer code

No Comments

No Known Activations