INDEX

Explanations

code structure and syntax related to variable definitions and types

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.5.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

<eos>

-0.57

</i>

-0.53

";

-0.51

↵

-0.51

</em>

-0.51

-0.50

</u>

-0.49

");

-0.48

-0.45

setupUi

-0.45

POSITIVE LOGITS

ⓧ

1.11

 Administrativna

1.03

 Diſ

0.95

 Anſ

0.95

 Majefty

0.93

 ―――――

0.91

RegressionTest

0.89

Tikang

0.89

QMetaType

0.88

 pleaſure

0.87

Activations Density 0.759%

code structure and syntax related to variable definitions and types

No Comments

No Known Activations