INDEX

Explanations

references to mathematical operations involving reshaping and array dimensions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 4-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_4/width_16k/average_l0_124

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.4.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

-0.65

васто

-0.43

 everything

-0.41

//</

-0.40

 smtplib

-0.40

 aquilo

-0.39

MILLIS

-0.38

UNRELATED

-0.37

ğaz

-0.37

utm

-0.37

POSITIVE LOGITS

shape

1.31

 shape

0.94

Demografia

0.92

 ProtoMessage

0.90

Shape

0.90

 Shape

0.87

SHAPE

0.86

 SHAPE

0.82

MigrationBuilder

0.76

complexType

0.74

Activations Density 0.141%

references to mathematical operations involving reshaping and array dimensions

No Comments

No Known Activations