INDEX

Explanations

code-related elements and attributes in a programming context

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

-0.54

“

-0.48

not

-0.48

 element

-0.47

-0.46

or

-0.44

POSITIVE LOGITS

 propOrder

1.35

 InputDecoration

1.13

findpost

1.03

 GetEnumerator

1.03

awtextra

1.00

 ModelExpression

0.97

fjspx

0.97

 intptr

0.97

 الرياضيه

0.93

Size

0.92

Activations Density 0.006%

code-related elements and attributes in a programming context

No Comments

No Known Activations