INDEX

Explanations

programming-related syntax, particularly function definitions and condition checks

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 23-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_23/width_16k/average_l0_75

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.23.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

ArrowToggle

-0.51

 Autorizaciones

-0.47

तिक

-0.45

Titled

-0.44

zyst

-0.44

bart

-0.44

ecraft

-0.43

orno

-0.42

 चीज़ों

-0.42

ူ

-0.42

POSITIVE LOGITS

 index

3.79

index

3.41

 Index

3.05

Index

2.83

 INDEX

2.56

INDEX

2.44

 indexes

2.38

 indices

2.24

 indexing

2.21

 indeks

2.12

Activations Density 0.167%

programming-related syntax, particularly function definitions and condition checks

No Comments

No Known Activations