INDEX

Explanations

Java programming constructs and data structures

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.21.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

rictions

-0.47

DAE

-0.44

Newswire

-0.44

stva

-0.42

 transfection

-0.40

ẨM

-0.39

 Stück

-0.39

Silen

-0.39

роне

-0.38

 Newswire

-0.38

POSITIVE LOGITS

map

1.00

Map

0.97

map

0.96

Map

0.95

 hash

0.94

 Maps

0.93

 Hash

0.92

hash

0.91

 maps

0.89

 HashMap

0.84

Activations Density 0.402%

Java programming constructs and data structures

No Comments

No Known Activations