INDEX

Explanations

names of individuals and entities related to various contexts

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 tkinter

-0.96

</caption>

-0.93

 >=",

-0.92

AIO

-0.91

Hentet

-0.90

"]);

-0.88

__":

-0.87

 StatefulWidget

-0.86

^(@)

-0.83

")));

-0.83

POSITIVE LOGITS

 SUBST

0.68

Pic

0.67

 vall

0.67

Inf

0.65

kem

0.64

 Belf

0.63

igh

0.63

 Vall

0.62

<h3>

0.62

 Mart

0.61

Activations Density 1.762%

names of individuals and entities related to various contexts

No Comments

No Known Activations