INDEX

Explanations

programming syntax and structure related to variable declarations and array manipulations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.20.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

**********/

-0.52

 Kraw

-0.50

***********/

-0.48

theria

-0.47

untamente

-0.47

íncia

-0.47

anged

-0.47

CLES

-0.47

óticas

-0.47

hant

-0.47

POSITIVE LOGITS

 length

1.57

len

1.39

 Length

1.32

length

1.31

len

1.27

 size

1.26

Length

1.24

 LENGTH

1.21

 lenght

1.21

Len

1.14

Activations Density 0.388%

programming syntax and structure related to variable declarations and array manipulations

No Comments

No Known Activations